Seminars

Understanding the neural mechanisms of reward-guided learning is a long-standing goal of computational neuroscience. Recent methodological innovations enable us to collect ever larger neural and behavioral datasets. This presents opportunities to achieve greater understanding of learning in the brain at scale, as well as methodological challenges. In the first part of the talk, I will discuss our recent insights into the mechanisms by which zebra finch songbirds learn to sing. Dopamine has been long thought to guide reward-based trial-and-error learning by encoding reward prediction errors. However, it is unknown whether the learning of natural behaviours, such as developmental vocal learning, occurs through dopamine-based reinforcement. Longitudinal recordings of dopamine and bird songs reveal that dopamine activity is indeed consistent with encoding a reward prediction error during naturalistic learning. In the second part of the talk, I will talk about recent work we are doing at DeepMind to develop tools for automatically discovering interpretable models of behavior directly from animal choice data. Our method, dubbed CogFunSearch, uses LLMs within an evolutionary search process in order to "discover" novel models in the form of Python programs that excel at accurately predicting animal behavior during reward-guided learning. The discovered programs reveal novel patterns of learning and choice behavior that update our understanding of how the brain solves reinforcement learning problems.

Cognitive maps confer animals with flexible intelligence by representing spatial, temporal, and abstract relationships that can be used to shape thought, planning, and behavior. Cognitive maps have been observed in the hippocampus, but their algorithmic form and the processes by which they are learned remain obscure. Here, we employed large-scale, longitudinal two-photon calcium imaging to record activity from thousands of neurons in the CA1 region of the hippocampus while mice learned to efficiently collect rewards from two subtly different versions of linear tracks in virtual reality. The results provide a detailed view of the formation of a cognitive map in the hippocampus. Throughout learning, both the animal behavior and hippocampal neural activity progressed through multiple intermediate stages, gradually revealing improved task representation that mirrored improved behavioral efficiency. The learning process led to progressive decorrelations in initially similar hippocampal neural activity within and across tracks, ultimately resulting in orthogonalized representations resembling a state machine capturing the inherent struture of the task. We show that a Hidden Markov Model (HMM) and a biologically plausible recurrent neural network trained using Hebbian learning can both capture core aspects of the learning dynamics and the orthogonalized representational structure in neural activity. In contrast, we show that gradient-based learning of sequence models such as Long Short-Term Memory networks (LSTMs) and Transformers do not naturally produce such orthogonalized representations. We further demonstrate that mice exhibited adaptive behavior in novel task settings, with neural activity reflecting flexible deployment of the state machine. These findings shed light on the mathematical form of cognitive maps, the learning rules that sculpt them, and the algorithms that promote adaptive behavior in animals. The work thus charts a course toward a deeper understanding of biological intelligence and offers insights toward developing more robust learning algorithms in artificial intelligence.

I will discuss work with Jack Lindsey modeling reinforcement learning for action selection in the basal ganglia. I will argue that the presence of multiple brain regions, in addition to the basal ganglia, that contribute to motor control motivates the need for an off-policy basal ganglia learning algorithm. I will then describe a biological implementation of such an algorithm that predicts tuning of dopamine neurons to a quantity we call "action surprise," in addition to reward prediction error. In the same model, an implementation of learning from a motor efference copy also predicts a novel solution to the problem of multiplexing feedforward and efference-related striatal activity. The solution exploits the difference between D1 and D2-expressing medium spiny neurons and leads to predictions about striatal dynamics.

Coping with threatening situations requires both identifying stimuli predicting danger and selecting adaptive behavioral responses in order to survive. The dorso medial prefrontal cortex (dmPFC) is a critical structure involved in the regulation of threat-related behaviour, yet it is still largely unclear how threat-predicting stimuli and defensive behaviours are associated within prefrontal networks in order to successfully drive adaptive responses. Over the past years, we used a combination we used a combination of extracellular recordings, neuronal decoding approaches, and state of the art optogenetic manipulations to identify key neuronal elements and mechanisms controlling defensive fear responses. I will present an overview of our recent work ranging from analyses of dedicated neuronal types and oscillatory and synchronization mechanisms to artificial intelligence approaches used to decode the activity or large population of neurons. Ultimately these analyses allowed the identification of high dimensional representations of defensive behavior unfolding within prefrontal networks.

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.

Behavior arises from the coordinated activity of numerous distinct brain regions. Modern experimental tools allow access to neural populations brain-wide, yet understanding such large-scale datasets necessitates scalable computational models to extract meaningful features of inter-region communication. In this talk, I will introduce Current-Based Decomposition (CURBD), an approach for inferring multi-region interactions using data-constrained recurrent neural network models. I will first show that CURBD accurately isolates inter-region currents in simulated networks with known dynamics. I will then apply CURBD to understand the brain-wide flow of information leading to behavioral state transitions in larval zebrafish. These examples will establish CURBD as a flexible, scalable framework to infer brain-wide interactions that are inaccessible from experimental measurements alone.