Topic: generalization

How can memories remain durable while adapting to new situations? Gisella Vetere examines how the neuronal ensembles encoding a memory change between initial learning and later recall, and how their reorganization across brain networks supports both precise recollection and generalization. Her research combines activity-dependent cell tagging, interventions in neural circuits and analyses across the brain to investigate these transformations. The talk considers how changes in memory representations influence flexible behavior, including circumstances in which that flexibility becomes maladapti

Develop communication-efficient, privacy-preserving distributed learning algorithms for streaming data in edge inference networks. The PRIDeL collaboration connects Inria, Simula and NYCU, combining theory or experiments on convergence, generalization, data freshness and differential privacy. The doctorate must be defended by 31 December 2026, and the appointment must provide a research environment distinct from the doctorate. The contract begins in France, with international visits encouraged. Appointment: 1 year, 4 months; advertised start 2027-01-01. 2 788 € gross monthly.

Deep networks are often thought of as black boxes. Their ability to encompass vast swathes of knowledge indeed makes them hard to explain. Yet many of their behaviours — generalization under overparametrization, grokking, OOD failures, neural scaling laws — recur across architectures and scales, and each, however surprising, can be reproduced and explained in controlled settings. I will review these efforts to identify and explain the universal phenomena of deep learning, and suggest that an LLM may amount to a sum of such tractable sub-phenomena, interpolative in nature. Finally, leaving scie

Daphne Koller of insitro discusses the differences between finding predictive patterns and identifying interventions that improve disease outcomes. The conversation examines biological data scarcity, structure and causality, failures in drug development and the limits of speeding up wet-lab work with AI agents. It also considers foundation models for biology, generalization beyond observed data, human evidence and scientific discovery. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Cristopher Moore connects computational complexity to questions about cognition and artificial intelligence. The discussion considers what makes a problem difficult, how rugged landscapes shape computation, and what complexity theory can contribute to understanding learning and generalization in brains and machines.

There is a fundamental tension between storing discrete traces of individual experiences, which allows recall of particular moments in our past without interference, and extracting regularities across these experiences, which supports generalization and prediction in similar situations in the future. One influential proposal for how the brain resolves this tension is that it separates the processes anatomically into Complementary Learning Systems, with the hippocampus rapidly encoding individual episodes and the neocortex slowly extracting regularities over days, months, and years. But this do

Developing scientifically-grounded theories for representation learning and generalization in artificial deep neural networks remains a grand challenge of fundamental interest to theoretical neuroscience and machine learning. I will discuss our work on one facet of this challenge — namely understanding generalization or “scaling laws” in learned neural networks as a function of basic control variables. I’ll discuss a taxonomy we develop that classifies different regimes of scaling behavior. We identify regimes where generalization exhibits universal scaling behavior and others where it can be

There is a fundamental tension between storing discrete traces of individual experiences, which allows recall of particular moments in our past without interference, and extracting regularities across these experiences, which supports generalization and prediction in similar situations in the future. One influential proposal for how the brain resolves this tension is that it separates the processes anatomically into Complementary Learning Systems, with the hippocampus rapidly encoding individual episodes and the neocortex slowly extracting regularities over days, months, and years. But this do

Humans and animals learn and plan with flexibility and efficiency well beyond that of modern Machine Learning methods. This is hypothesized to owe in part to the ability of animals to build structured representations of their environments, and modulate these representations to rapidly adapt to new settings. In the first part of this talk, I will discuss theoretical work describing how learned representations in hippocampus enable rapid adaptation to new goals by learning predictive representations. I will also cover work extending this account, in which we show how the predictive model can be

Humans and animals learn and plan with flexibility and efficiency well beyond that of modern Machine Learning methods. This is hypothesized to owe in part to the ability of animals to build structured representations of their environments, and modulate these representations to rapidly adapt to new settings. In the first part of this talk, I will discuss theoretical work describing how learned representations in hippocampus enable rapid adaptation to new goals by learning predictive representations, while entorhinal cortex compresses these predictive representations with spectral methods that s

Humans are natural teachers; learning through instruction is one of the most fundamental ways that we learn. Interactive Task Learning (ITL) is an emerging research agenda that studies the design of complex intelligent robots that can acquire new knowledge through natural human teacher-robot learner interactions. ITL methods are particularly useful for designing intelligent robots whose behavior can be adapted by humans collaborating with them. In this talk, I will summarize our recent findings on the structure that human instruction naturally has and motivate an intelligent system design that

Neuronal computation is mediated by spikes, yet it is unclear what the benefits of discrete spiking dynamics over continuous firing rates are. Many theoretical and computational studies treat single neurons as continuous units and their output as an effective firing rate. These works view spiking dynamics as a biophysical constraint, e.g., for energy efficiency. Conversely, other theories suggest that the exact timings of single spikes are meaningful. We propose a novel theory that shows the benefits of spiking dynamics on neural computation. In particular, we show that spiking neural dynamics

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

Paul Middlebrooks and Patryk Laurent examine how principles drawn from brains could help artificial intelligence learn from the real world. Laurent connects experience in neuroscience and AI with questions about perception, action, prediction and generalization. The conversation considers learning from continuous video, what embodied robotic systems reveal about intelligence, the relationship between language models and other forms of learning, and which biological details may matter when developing more capable AI.

How do people learn in real-world environments where the space of possible actions can be vast or even infinite? The study of human learning has made rapid progress in past decades, from discovering the neural substrate of reward prediction errors, to building AI capable of mastering the game of Go. Yet this line of research has primarily focused on learning through repeated interactions with the same stimuli. How are humans able to rapidly adapt to novel situations and learn from such sparse examples? I propose a theory of how generalization guides human learning, by making predictions about

The curse of dimensionality plagues models of reinforcement learning and decision-making. The process of abstraction solves this by constructing abstract variables describing features shared by different specific instances, reducing dimensionality and enabling generalization in novel situations. Here we characterized neural representations in monkeys performing a task where a hidden variable described the temporal statistics of stimulus-response-outcome mappings. Abstraction was defined operationally using the generalization performance of neural decoders across task conditions not used for tr

Humans’ ability to perceive and abstract relational structure is fundamental to our learning. It allows us to acquire knowledge all the way from linguistic grammar to spatial knowledge to social structures. How does a learner begin to perceive structure in the world? Why do we sometimes fail to see structural commonalities across events? To begin to answer these questions, I attempt to bridge two large, yet somewhat separate research traditions in understanding human’s structural abstraction: rule learning (Marcus et al., 1999) and analogical learning (Gentner, 1989). On the one hand, rule lea

Cognitive architectures are attempts to build larger-scale models of minds. This talk will explore how structure-mapping models of analogical matching, retrieval, and generalization are used in the Companion cognitive architecture. Examples will include modeling conceptual change, learning by reading, and analogical Q/A training.

Practicing a visual task leads to long-lasting perceptual improvements in humans and other animals. However, the generalization of Visual Learning (VL) to unseen conditions varies across different tasks. Particularly, it has been shown that learning ‘easy’ visual tasks leads to better generalization than learning ‘hard’ ones. Moreover, experimental evidence suggests that greater generalizability in VL can be achieved through sequential curriculum training, specifically by training on ‘easier’ versions of a task before progressing to ‘harder’ versions. Yet, a neurocomputational explanation for