Prof. Dr. Jochen Triesch

Applications are invited for a PhD or post-doc position at the Frankfurt Institute for Advanced Studies (FIAS) to develop neural network-based computational models of active auditory perception. The project will address how the brain adapts sensory coding strategies, attentional processing, and behavior to optimize active auditory perception in its recurrent processing architecture. The project is part of Germany’s priority program 'Sensing LOOPS: Cortico-subcortical Interactions for Adaptive Sensing' and offers opportunities for collaboration with experimental labs, including the lab of Julio Hechavarrria in Frankfurt.

Probing neural population dynamics with recurrent neural networks

Large-scale recordings of neural activity are providing new opportunities to study network-level dynamics with unprecedented detail. However, the sheer volume of data and its dynamical complexity are major barriers to uncovering and interpreting these dynamics. I will present latent factor analysis via dynamical systems, a sequential autoencoding approach that enables inference of dynamics from neuronal population spiking activity on single trials and millisecond timescales. I will also discuss recent adaptations of the method to uncover dynamics from neural activity recorded via 2P Calcium imaging. Finally, time permitting, I will mention recent efforts to improve the interpretability of deep-learning based dynamical systems models.

The centrality of population-level factors to network computation is demonstrated by a versatile approach for training spiking networks

Neural activity is often described in terms of population-level factors extracted from the responses of many neurons. Factors provide a lower-dimensional description with the aim of shedding light on network computations. Yet, mechanistically, computations are performed not by continuously valued factors but by interactions among neurons that spike discretely and variably. Models provide a means of bridging these levels of description. We developed a general method for training model networks of spiking neurons by leveraging factors extracted from either data or firing-rate-based networks. In addition to providing a useful model-building framework, this formalism illustrates how reliable and continuously valued factors can arise from seemingly stochastic spiking. Our framework establishes procedures for embedding this property in network models with different levels of realism. The relationship between spikes and factors in such networks provides a foundation for interpreting (and subtly redefining) commonly used quantities such as firing rates.

Extracting computational mechanisms from neural data using low-rank RNNs

An influential theory in systems neuroscience suggests that brain function can be understood through low-dimensional dynamics [Vyas et al 2020]. However, a challenge in this framework is that a single computational task may involve a range of dynamic processes. To understand which processes are at play in the brain, it is important to use data on neural activity to constrain models. In this study, we present a method for extracting low-dimensional dynamics from data using low-rank recurrent neural networks (lrRNNs), a highly expressive and understandable type of model [Mastrogiuseppe & Ostojic 2018, Dubreuil, Valente et al. 2022]. We first test our approach using synthetic data created from full-rank RNNs that have been trained on various brain tasks. We find that lrRNNs fitted to neural activity allow us to identify the collective computational processes and make new predictions for inactivations in the original RNNs. We then apply our method to data recorded from the prefrontal cortex of primates during a context-dependent decision-making task. Our approach enables us to assign computational roles to the different latent variables and provides a mechanistic model of the recorded dynamics, which can be used to perform in silico experiments like inactivations and provide testable predictions.

Analyzing artificial neural networks to understand the brain

In the first part of this talk I will present work showing that recurrent neural networks can replicate broad behavioral patterns associated with dynamic visual object recognition in humans. An analysis of these networks shows that different types of recurrence use different strategies to solve the object recognition problem. The similarities between artificial neural networks and the brain presents another opportunity, beyond using them just as models of biological processing. In the second part of this talk, I will discuss—and solicit feedback on—a proposed research plan for testing a wide range of analysis tools frequently applied to neural data on artificial neural networks. I will present the motivation for this approach as well as the form the results could take and how this would benefit neuroscience.

Training Dynamic Spiking Neural Network via Forward Propagation Through Time

With recent advances in learning algorithms, recurrent networks of spiking neurons are achieving performance competitive with standard recurrent neural networks. Still, these learning algorithms are limited to small networks of simple spiking neurons and modest-length temporal sequences, as they impose high memory requirements, have difficulty training complex neuron models, and are incompatible with online learning.Taking inspiration from the concept of Liquid Time-Constant (LTCs), we introduce a novel class of spiking neurons, the Liquid Time-Constant Spiking Neuron (LTC-SN), resulting in functionality similar to the gating operation in LSTMs. We integrate these neurons in SNNs that are trained with FPTT and demonstrate that thus trained LTC-SNNs outperform various SNNs trained with BPTT on long sequences while enabling online learning and drastically reducing memory complexity. We show this for several classical benchmarks that can easily be varied in sequence length, like the Add Task and the DVS-gesture benchmark. We also show how FPTT-trained LTC-SNNs can be applied to large convolutional SNNs, where we demonstrate novel state-of-the-art for online learning in SNNs on a number of standard benchmarks (S-MNIST, R-MNIST, DVS-GESTURE) and also show that large feedforward SNNs can be trained successfully in an online manner to near (Fashion-MNIST, DVS-CIFAR10) or exceeding (PS-MNIST, R-MNIST) state-of-the-art performance as obtained with offline BPTT. Finally, the training and memory efficiency of FPTT enables us to directly train SNNs in an end-to-end manner at network sizes and complexity that was previously infeasible: we demonstrate this by training in an end-to-end fashion the first deep and performant spiking neural network for object localization and recognition. Taken together, we out contribution enable for the first time training large-scale complex spiking neural network architectures online and on long temporal sequences.

Towards multi-system network models for cognitive neuroscience

Artificial neural networks can be useful for studying brain functions. In cognitive neuroscience, recurrent neural networks are often used to model cognitive functions. I will first offer my opinion on what is missing in the classical use of recurrent neural networks. Then I will discuss two lines of ongoing efforts in our group to move beyond the classical recurrent neural networks by studying multi-system neural networks (the talk will focus on two-system networks). These are networks that combine modules for several neural systems, such as vision, audition, prefrontal, hippocampal systems. I will showcase how multi-system networks can potentially be constrained by experimental data in fundamental ways and at scale.

Aligned and Oblique Dynamics in Recurrent Neural Networks

Talk & Tutorial

Flexible multitask computation in recurrent networks utilizes shared dynamical motifs

Flexible computation is a hallmark of intelligent behavior. Yet, little is known about how neural networks contextually reconfigure for different computations. Humans are able to perform a new task without extensive training, presumably through the composition of elementary processes that were previously learned. Cognitive scientists have long hypothesized the possibility of a compositional neural code, where complex neural computations are made up of constituent components; however, the neural substrate underlying this structure remains elusive in biological and artificial neural networks. Here we identified an algorithmic neural substrate for compositional computation through the study of multitasking artificial recurrent neural networks. Dynamical systems analyses of networks revealed learned computational strategies that mirrored the modular subtask structure of the task-set used for training. Dynamical motifs such as attractors, decision boundaries and rotations were reused across different task computations. For example, tasks that required memory of a continuous circular variable repurposed the same ring attractor. We show that dynamical motifs are implemented by clusters of units and are reused across different contexts, allowing for flexibility and generalization of previously learned computation. Lesioning these clusters resulted in modular effects on network performance: a lesion that destroyed one dynamical motif only minimally perturbed the structure of other dynamical motifs. Finally, modular dynamical motifs could be reconfigured for fast transfer learning. After slow initial learning of dynamical motifs, a subsequent faster stage of learning reconfigured motifs to perform novel tasks. This work contributes to a more fundamental understanding of compositional computation underlying flexible general intelligence in neural systems. We present a conceptual framework that establishes dynamical motifs as a fundamental unit of computation, intermediate between the neuron and the network. As more whole brain imaging studies record neural activity from multiple specialized systems simultaneously, the framework of dynamical motifs will guide questions about specialization and generalization across brain regions.

Online Training of Spiking Recurrent Neural Networks​ With Memristive Synapses

Spiking recurrent neural networks (RNNs) are a promising tool for solving a wide variety of complex cognitive and motor tasks, due to their rich temporal dynamics and sparse processing. However training spiking RNNs on dedicated neuromorphic hardware is still an open challenge. This is due mainly to the lack of local, hardware-friendly learning mechanisms that can solve the temporal credit assignment problem and ensure stable network dynamics, even when the weight resolution is limited. These challenges are further accentuated, if one resorts to using memristive devices for in-memory computing to resolve the von-Neumann bottleneck problem, at the expense of a substantial increase in variability in both the computation and the working memory of the spiking RNNs. In this talk, I will present our recent work where we introduced a PyTorch simulation framework of memristive crossbar arrays that enables accurate investigation of such challenges. I will show that recently proposed e-prop learning rule can be used to train spiking RNNs whose weights are emulated in the presented simulation framework. Although e-prop locally approximates the ideal synaptic updates, it is difficult to implement the updates on the memristive substrate due to substantial device non-idealities. I will mention several widely adapted weight update schemes that primarily aim to cope with these device non-idealities and demonstrate that accumulating gradients can enable online and efficient training of spiking RNN on memristive substrates.

Optimal information loading into working memory in prefrontal cortex

Working memory involves the short-term maintenance of information and is critical in many tasks. The neural circuit dynamics underlying working memory remain poorly understood, with different aspects of prefrontal cortical (PFC) responses explained by different putative mechanisms. By mathematical analysis, numerical simulations, and using recordings from monkey PFC, we investigate a critical but hitherto ignored aspect of working memory dynamics: information loading. We find that, contrary to common assumptions, optimal information loading involves inputs that are largely orthogonal, rather than similar, to the persistent activities observed during memory maintenance. Using a novel, theoretically principled metric, we show that PFC exhibits the hallmarks of optimal information loading and we find that such dynamics emerge naturally as a dynamical strategy in task-optimized recurrent neural networks. Our theory unifies previous, seemingly conflicting theories of memory maintenance based on attractor or purely sequential dynamics, and reveals a normative principle underlying the widely observed phenomenon of dynamic coding in PFC.

An investigation of perceptual biases in spiking recurrent neural networks trained to discriminate time intervals

Magnitude estimation and stimulus discrimination tasks are affected by perceptual biases that cause the stimulus parameter to be perceived as shifted toward the mean of its distribution. These biases have been extensively studied in psychophysics and, more recently and to a lesser extent, with neural activity recordings. New computational techniques allow us to train spiking recurrent neural networks on the tasks used in the experiments. This provides us with another valuable tool with which to investigate the network mechanisms responsible for the biases and how behavior could be modeled. As an example, in this talk I will consider networks trained to discriminate the durations of temporal intervals. The trained networks presented the contraction bias, even though they were trained with a stimulus sequence without temporal correlations. The neural activity during the delay period carried information about the stimuli of the current trial and previous trials, this being one of the mechanisms that originated the contraction bias. The population activity described trajectories in a low-dimensional space and their relative locations depended on the prior distribution. The results can be modeled as an ideal observer that during the delay period sees a combination of the current and the previous stimuli. Finally, I will describe how the neural trajectories in state space encode an estimate of the interval duration. The approach could be applied to other cognitive tasks.

Parametric control of flexible timing through low-dimensional neural manifolds

Biological brains possess an exceptional ability to infer relevant behavioral responses to a wide range of stimuli from only a few examples. This capacity to generalize beyond the training set has been proven particularly challenging to realize in artificial systems. How neural processes enable this capacity to extrapolate to novel stimuli is a fundamental open question. A prominent but underexplored hypothesis suggests that generalization is facilitated by a low-dimensional organization of collective neural activity, yet evidence for the underlying neural mechanisms remains wanting. Combining network modeling, theory and neural data analysis, we tested this hypothesis in the framework of flexible timing tasks, which rely on the interplay between inputs and recurrent dynamics. We first trained recurrent neural networks on a set of timing tasks while minimizing the dimensionality of neural activity by imposing low-rank constraints on the connectivity, and compared the performance and generalization capabilities with networks trained without any constraint. We then examined the trained networks, characterized the dynamical mechanisms underlying the computations, and verified their predictions in neural recordings. Our key finding is that low-dimensional dynamics strongly increases the ability to extrapolate to inputs outside of the range used in training. Critically, this capacity to generalize relies on controlling the low-dimensional dynamics by a parametric contextual input. We found that this parametric control of extrapolation was based on a mechanism where tonic inputs modulate the dynamics along non-linear manifolds in activity space while preserving their geometry. Comparisons with neural recordings in the dorsomedial frontal cortex of macaque monkeys performing flexible timing tasks confirmed the geometric and dynamical signatures of this mechanism. Altogether, our results tie together a number of previous experimental findings and suggest that the low-dimensional organization of neural dynamics plays a central role in generalizable behaviors.

Theory of recurrent neural networks – from parameter inference to intrinsic timescales in spiking networks

NMC4 Short Talk: Predictive coding is a consequence of energy efficiency in recurrent neural networks

Predictive coding represents a promising framework for understanding brain function, postulating that the brain continuously inhibits predictable sensory input, ensuring a preferential processing of surprising elements. A central aspect of this view on cortical computation is its hierarchical connectivity, involving recurrent message passing between excitatory bottom-up signals and inhibitory top-down feedback. Here we use computational modelling to demonstrate that such architectural hard-wiring is not necessary. Rather, predictive coding is shown to emerge as a consequence of energy efficiency, a fundamental requirement of neural processing. When training recurrent neural networks to minimise their energy consumption while operating in predictive environments, the networks self-organise into prediction and error units with appropriate inhibitory and excitatory interconnections and learn to inhibit predictable sensory input. We demonstrate that prediction units can reliably be identified through biases in their median preactivation, pointing towards a fundamental property of prediction units in the predictive coding framework. Moving beyond the view of purely top-down driven predictions, we demonstrate via virtual lesioning experiments that networks perform predictions on two timescales: fast lateral predictions among sensory units and slower prediction cycles that integrate evidence over time. Our results, which replicate across two separate data sets, suggest that predictive coding can be interpreted as a natural consequence of energy efficiency. More generally, they raise the question which other computational principles of brain function can be understood as a result of physical constraints posed by the brain, opening up a new area of bio-inspired, machine learning-powered neuroscience research.

NMC4 Short Talk: A theory for the population rate of adapting neurons disambiguates mean vs. variance-driven dynamics and explains log-normal response statistics

Recently, the field of computational neuroscience has seen an explosion of the use of trained recurrent network models (RNNs) to model patterns of neural activity. These RNN models are typically characterized by tuned recurrent interactions between rate 'units' whose dynamics are governed by smooth, continuous differential equations. However, the response of biological single neurons is better described by all-or-none events - spikes - that are triggered in response to the processing of their synaptic input by the complex dynamics of their membrane. One line of research has attempted to resolve this discrepancy by linking the average firing probability of a population of simplified spiking neuron models to rate dynamics similar to those used for RNN units. However, challenges remain to account for complex temporal dependencies in the biological single neuron response and for the heterogeneity of synaptic input across the population. Here, we make progress by showing how to derive dynamic rate equations for a population of spiking neurons with multi-timescale adaptation properties - as this was shown to accurately model the response of biological neurons - while they receive independent time-varying inputs, leading to plausible asynchronous activity in the network. The resulting rate equations yield an insightful segregation of the population's response into dynamics that are driven by the mean signal received by the neural population, and dynamics driven by the variance of the input across neurons, with respective timescales that are in agreement with slice experiments. Further, these equations explain how input variability can shape log-normal instantaneous rate distributions across neurons, as observed in vivo. Our results help interpret properties of the neural population response and open the way to investigating whether the more biologically plausible and dynamically complex rate model we derive could provide useful inductive biases if used in an RNN to solve specific tasks.

NMC4 Short Talk: Different hypotheses on the role of the PFC in solving simple cognitive tasks

Low-dimensional population dynamics can be observed in neural activity recorded from the prefrontal cortex (PFC) of subjects performing simple cognitive tasks. Many studies have shown that recurrent neural networks (RNNs) trained on the same tasks can reproduce qualitatively these state space trajectories, and have used them as models of how neuronal dynamics implement task computations. The PFC is also viewed as a conductor that organizes the communication between cortical areas and provides contextual information. It is then not clear what is its role in solving simple cognitive tasks. Do the low-dimensional trajectories observed in the PFC really correspond to the computations that it performs? Or do they indirectly reflect the computations occurring within the cortical areas projecting to the PFC? To address these questions, we modelled cortical areas with a modular RNN and equipped it with a PFC-like cognitive system. When trained on cognitive tasks, this multi-system brain model can reproduce the low-dimensional population responses observed in neuronal activity as well as classical RNNs. Qualitatively different mechanisms can emerge from the training process when varying some details of the architecture such as the time constants. In particular, there is one class of models where it is the dynamics of the cognitive system that is implementing the task computations, and another where the cognitive system is only necessary to provide contextual information about the task rule as task performance is not impaired when preventing the system from accessing the task inputs. These constitute two different hypotheses about the causal role of the PFC in solving simple cognitive tasks, which could motivate further experiments on the brain.

NMC4 Keynote: An all-natural deep recurrent neural network architecture for flexible navigation

A wide variety of animals and some artificial agents can adapt their behavior to changing cues, contexts, and goals. But what neural network architectures support such behavioral flexibility? Agents with loosely structured network architectures and random connections can be trained over millions of trials to display flexibility in specific tasks, but many animals must adapt and learn with much less experience just to survive. Further, it has been challenging to understand how the structure of trained deep neural networks relates to their functional properties, an important objective for neuroscience. In my talk, I will use a combination of behavioral, physiological and connectomic evidence from the fly to make the case that the built-in modularity and structure of its networks incorporate key aspects of the animal’s ecological niche, enabling rapid flexibility by constraining learning to operate on a restricted parameter set. It is not unlikely that this is also a feature of many biological neural networks across other animals, large and small, and with and without vertebrae.

Recurrent network dynamics lead to interference in sequential learning

Learning in real life is often sequential: A learner first learns task A, then task B. If the tasks are related, the learner may adapt the previously learned representation instead of generating a new one from scratch. Adaptation may ease learning task B but may also decrease the performance on task A. Such interference has been observed in experimental and machine learning studies. In the latter case, it is mediated by correlations between weight updates for the different tasks. In typical applications, like image classification with feed-forward networks, these correlated weight updates can be traced back to input correlations. For many neuroscience tasks, however, networks need to not only transform the input, but also generate substantial internal dynamics. Here we illuminate the role of internal dynamics for interference in recurrent neural networks (RNNs). We analyze RNNs trained sequentially on neuroscience tasks with gradient descent and observe forgetting even for orthogonal tasks. We find that the degree of interference changes systematically with tasks properties, especially with emphasis on input-driven over autonomously generated dynamics. To better understand our numerical observations, we thoroughly analyze a simple model of working memory: For task A, a network is presented with an input pattern and trained to generate a fixed point aligned with this pattern. For task B, the network has to memorize a second, orthogonal pattern. Adapting an existing representation corresponds to the rotation of the fixed point in phase space, as opposed to the emergence of a new one. We show that the two modes of learning – rotation vs. new formation – are directly linked to recurrent vs. input-driven dynamics. We make this notion precise in a further simplified, analytically tractable model, where learning is restricted to a 2x2 matrix. In our analysis of trained RNNs, we also make the surprising observation that, across different tasks, larger random initial connectivity reduces interference. Analyzing the fixed point task reveals the underlying mechanism: The random connectivity strongly accelerates the learning mode of new formation, and has less effect on rotation. The prior thus wins the race to zero loss, and interference is reduced. Altogether, our work offers a new perspective on sequential learning in recurrent networks, and the emphasis on internally generated dynamics allows us to take the history of individual learners into account.

Untangling brain wide current flow using neural network models

Rajanlab designs neural network models constrained by experimental data, and reverse engineers them to figure out how brain circuits function in health and disease. Recently, we have been developing a powerful new theory-based framework for “in-vivo tract tracing” from multi-regional neural activity collected experimentally. We call this framework CURrent-Based Decomposition (CURBD). CURBD employs recurrent neural networks (RNNs) directly constrained, from the outset, by time series measurements acquired experimentally, such as Ca2+ imaging or electrophysiological data. Once trained, these data-constrained RNNs let us infer matrices quantifying the interactions between all pairs of modeled units. Such model-derived “directed interaction matrices” can then be used to separately compute excitatory and inhibitory input currents that drive a given neuron from all other neurons. Therefore different current sources can be de-mixed – either within the same region or from other regions, potentially brain-wide – which collectively give rise to the population dynamics observed experimentally. Source de-mixed currents obtained through CURBD allow an unprecedented view into multi-region mechanisms inaccessible from measurements alone. We have applied this method successfully to several types of neural data from our experimental collaborators, e.g., zebrafish (Deisseroth lab, Stanford), mice (Harvey lab, Harvard), monkeys (Rudebeck lab, Sinai), and humans (Rutishauser lab, Cedars Sinai), where we have discovered both directed interactions brain wide and inter-area currents during different types of behaviors. With this powerful framework based on data-constrained multi-region RNNs and CURrent Based Decomposition (CURBD), we ask if there are conserved multi-region mechanisms across different species, as well as identify key divergences.

Interacting synapses stabilise both learning and neuronal dynamics in biological networks

Distinct synapses influence one another when they undergo changes, with unclear consequences for neuronal dynamics and function. Here we show that synapses can interact such that excitatory currents are naturally normalised and balanced by inhibitory inputs. This happens when classical spike-timing dependent synaptic plasticity rules are extended by additional mechanisms that incorporate the influence of neighbouring synaptic currents and regulate the amplitude of efficacy changes accordingly. The resulting control of excitatory plasticity by inhibitory activation, and vice versa, gives rise to quick and long-lasting memories as seen experimentally in receptive field plasticity paradigms. In models with additional dendritic structure, we observe experimentally reported clustering of co-active synapses that depends on initial connectivity and morphology. Finally, in recurrent neural networks, rich and stable dynamics with high input sensitivity emerge, providing transient activity that resembles recordings from the motor cortex. Our model provides a general framework for codependent plasticity that frames individual synaptic modifications in the context of population-wide changes, allowing us to connect micro-level physiology with behavioural phenomena.

Inferring brain-wide current flow using data-constrained neural network models

Rajanlab designs neural network models constrained by experimental data, and reverse engineers them to figure out how brain circuits function in health and disease. Recently, we have been developing a powerful new theory-based framework for “in-vivo tract tracing” from multi-regional neural activity collected experimentally. We call this framework CURrent-Based Decomposition (CURBD). CURBD employs recurrent neural networks (RNNs) directly constrained, from the outset, by time series measurements acquired experimentally, such as Ca2+ imaging or electrophysiological data. Once trained, these data-constrained RNNs let us infer matrices quantifying the interactions between all pairs of modeled units. Such model-derived “directed interaction matrices” can then be used to separately compute excitatory and inhibitory input currents that drive a given neuron from all other neurons. Therefore different current sources can be de-mixed – either within the same region or from other regions, potentially brain-wide – which collectively give rise to the population dynamics observed experimentally. Source de-mixed currents obtained through CURBD allow an unprecedented view into multi-region mechanisms inaccessible from measurements alone. We have applied this method successfully to several types of neural data from our experimental collaborators, e.g., zebrafish (Deisseroth lab, Stanford), mice (Harvey lab, Harvard), monkeys (Rudebeck lab, Sinai), and humans (Rutishauser lab, Cedars Sinai), where we have discovered both directed interactions brain wide and inter-area currents during different types of behaviors. With this framework based on data-constrained multi-region RNNs and CURrent Based Decomposition (CURBD), we can ask if there are conserved multi-region mechanisms across different species, as well as identify key divergences.

Using noise to probe recurrent neural network structure and prune synapses

Many networks in the brain are sparsely connected, and the brain eliminates synapses during development and learning. How could the brain decide which synapses to prune? In a recurrent network, determining the importance of a synapse between two neurons is a difficult computational problem, depending on the role that both neurons play and on all possible pathways of information flow between them. Noise is ubiquitous in neural systems, and often considered an irritant to be overcome. In the first part of this talk, I will suggest that noise could play a functional role in synaptic pruning, allowing the brain to probe network structure and determine which synapses are redundant. I will introduce a simple, local, unsupervised plasticity rule that either strengthens or prunes synapses using only synaptic weight and the noise-driven covariance of the neighboring neurons. For a subset of linear and rectified-linear networks, this rule provably preserves the spectrum of the original matrix and hence preserves network dynamics even when the fraction of pruned synapses asymptotically approaches 1. The plasticity rule is biologically-plausible and may suggest a new role for noise in neural computation. Time permitting, I will then turn to the problem of extracting structure from neural population data sets using dimensionality reduction methods. I will argue that nonlinear structures naturally arise in neural data and show how these nonlinearities cause linear methods of dimensionality reduction, such as Principal Components Analysis, to fail dramatically in identifying low-dimensional structure.

Theory of gating in recurrent neural networks

Recurrent neural networks (RNNs) are powerful dynamical models, widely used in machine learning (ML) for processing sequential data, and also in neuroscience, to understand the emergent properties of networks of real neurons. Prior theoretical work in understanding the properties of RNNs has focused on models with additive interactions. However, real neurons can have gating i.e. multiplicative interactions, and gating is also a central feature of the best performing RNNs in machine learning. Here, we develop a dynamical mean-field theory (DMFT) to study the consequences of gating in RNNs. We use random matrix theory to show how gating robustly produces marginal stability and line attractors – important mechanisms for biologically-relevant computations requiring long memory. The long-time behavior of the gated network is studied using its Lyapunov spectrum, and the DMFT is used to provide a novel analytical expression for the maximum Lyapunov exponent demonstrating its close relation to relaxation-time of the dynamics. Gating is also shown to give rise to a novel, discontinuous transition to chaos, where the proliferation of critical points (topological complexity) is decoupled from the appearance of chaotic dynamics (dynamical complexity), contrary to a seminal result for additive RNNs. Critical surfaces and regions of marginal stability in the parameter space are indicated in phase diagrams, thus providing a map for principled parameter choices for ML practitioners. Finally, we develop a field-theory for gradients that arise in training, by incorporating the adjoint sensitivity framework from control theory in the DMFT. This paves the way for the use of powerful field-theoretic techniques to study training/gradients in large RNNs.

E-prop: A biologically inspired paradigm for learning in recurrent networks of spiking neurons

Transformative advances in deep learning, such as deep reinforcement learning, usually rely on gradient-based learning methods such as backpropagation through time (BPTT) as a core learning algorithm. However, BPTT is not argued to be biologically plausible, since it requires to a propagate gradients backwards in time and across neurons. Here, we propose e-prop, a novel gradient-based learning method with local and online weight update rules for recurrent neural networks, and in particular recurrent spiking neural networks (RSNNs). As a result, e-prop has the potential to provide a substantial fraction of the power of deep learning to RSNNs. In this presentation, we will motivate e-prop from the perspective of recent insights in neuroscience and show how these have to be combined to form an algorithm for online gradient descent. The mathematical results will be supported by empirical evidence in supervised and reinforcement learning tasks. We will also discuss how limitations that are inherited from gradient-based learning methods, such as sample-efficiency, can be addressed by considering an evolution-like optimization that enhances learning on particular task families. The emerging learning architecture can be used to learn tasks by a single demonstration, hence enabling one-shot learning.

Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks

The emergence of brain-inspired neuromorphic computing as a paradigm for edge AI is motivating the search for high-performance and efficient spiking neural networks to run on this hardware. However, compared to classical neural networks in deep learning, current spiking neural networks lack competitive performance in compelling areas. Here, for sequential and streaming tasks, we demonstrate how spiking recurrent neural networks (SRNN) using adaptive spiking neurons are able to achieve state-of-the-art performance compared to other spiking neural networks and almost reach or exceed the performance of classical recurrent neural networks (RNNs) while exhibiting sparse activity. From this, we calculate a 100x energy improvement for our SRNNs over classical RNNs on the harder tasks. We find in particular that adapting the timescales of spiking neurons is crucial for achieving such performance, and we demonstrate the performance for SRNNs for different spiking neuron models.

Disentangling the roles of dimensionality and cell categories in neural computations

The description of neural computations currently relies on two competing views: (i) a classical single-cell view that aims to relate the activity of individual neurons to sensory or behavioural variables, and organize them into functional classes; (ii) a more recent population view that instead characterises computations in terms of collective neural trajectories, and focuses on the dimensionality of these trajectories as animals perform tasks. How the two key concepts of functional cell classes and low-dimensional trajectories interact to shape neural computations is however at present not understood. Here I will address this question by combining machine-learning tools for training recurrent neural networks with reverse-engineering and theoretical analyses of network dynamics.

Biological-plausible learning with a two compartment neuron model in recurrent neural networks

Bernstein Conference 2024

Identifying task-specific dynamics in recurrent neural networks using Dynamical Similarity Analysis

Bernstein Conference 2024

Inferring stochastic low-rank recurrent neural networks from neural data

Bernstein Conference 2024

Shaping Low-Rank Recurrent Neural Networks with Biological Learning Rules

Bernstein Conference 2024

Unraveling perceptual biases: Insights from spiking recurrent neural networks

Bernstein Conference 2024

A high-throughput pipeline for evaluating recurrent neural networks on multiple datasets

COSYNE 2022

Gain-mediated statistical adaptation in recurrent neural networks

COSYNE 2022

Gain-mediated statistical adaptation in recurrent neural networks

COSYNE 2022

A high-throughput pipeline for evaluating recurrent neural networks on multiple datasets

COSYNE 2022

Hippocampal representations emerge when training recurrent neural networks on a memory dependent maze navigation task

COSYNE 2022

Hippocampal representations emerge when training recurrent neural networks on a memory dependent maze navigation task

COSYNE 2022

Operative Dimensions in High-Dimensional Connectivity of Recurrent Neural Networks

COSYNE 2022

Operative Dimensions in High-Dimensional Connectivity of Recurrent Neural Networks

COSYNE 2022

Phase dependent maintenance of temporal order in biological and artificial recurrent neural networks

COSYNE 2022

Phase dependent maintenance of temporal order in biological and artificial recurrent neural networks

COSYNE 2022

Predicting connectivity of motion-processing neurons with recurrent neural networks

COSYNE 2022

Predicting connectivity of motion-processing neurons with recurrent neural networks

COSYNE 2022

The shared geometry of biological and recurrent neural network dynamics

COSYNE 2023

Discrete communication mediates effective regularization in recurrent neural networks

COSYNE 2023

Dissecting modular recurrent neural networks trained to perform un-cued task switching

COSYNE 2023

Non-stationary recurrent neural networks for reconstructing computational dynamics of rule learning

COSYNE 2023

Sequential learning in recurrent neural networks create memory traces of learned tasks

COSYNE 2023

Signatures of belief representations in recurrent neural networks and prefrontal cortex

COSYNE 2023

How Symmetry and Self-Coupling Shape Dynamics and Trainability of Recurrent Neural Networks

COSYNE 2023

A time-resolved theory of information encoding in recurrent neural networks

COSYNE 2023

Composing computational primitives in recurrent neural networks

COSYNE 2025

Constrained Multi-Regional Recurrent Neural Networks Elucidate Distributed Motor Timing Dynamics

COSYNE 2025

Covariance spectrum in nonlinear recurrent neural networks and transition to chaos

COSYNE 2025

Dynamically Learning to Remember in Recurrent Neural Networks

COSYNE 2025

Inferring stochastic low-rank recurrent neural networks from neural data

COSYNE 2025

Learning flexible decision-making in rats and recurrent neural networks

COSYNE 2025

Slow transition to chaos and robust reservoir computing in recurrent neural networks with heavy-tailed distributed synaptic weights

COSYNE 2025

Using a recurrent neural network to predict noradrenaline release by locus coeruleus neurons based on facial features in mice

COSYNE 2025

Reaction time variability in a delayed memory saccade task replicated by a recurrent neural network model

FENS Forum 2024

Behavioral Classification of Sequential Neural Activity Using Time Varying Recurrent Neural Networks

Neuromatch 5

Perceptual adaptation leads to changes in encoding accuracy that match those of a recurrent neural network optimized to predict the future

Neuromatch 5

Theory of phase coding in recurrent neural networks

Neuromatch 5