Arna Ghosh

Brain-like learning with exponentiated gradients

Jonathan Cornford

Roman Pogodin

Kaiwen Sheng

Brendan A. Bicknell

Olivier Codol

Beverley A. Clark

Guillaume Lajoie

2024-10-26

bioRxiv (preprint)

Harnessing small projectors and multiple views for efficient vision pretraining

Kumar Krishna Agrawal

Shagun Sodhani

Adam M. Oberman

2024-09-25

NeurIPS.cc/2024/Conference (poster)

Learning Successor Features the Simple Way

Christos Kaplanis

In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference … (see more)in non-stationary environments. Successor Features (SFs) offer a potential solution to this challenge. However, canonical techniques for learning SFs from pixel-level observations often lead to representation collapse, wherein representations degenerate and fail to capture meaningful variations in the data. More recent methods for learning SFs can avoid representation collapse, but they often involve complex losses and multiple learning phases, reducing their efficiency. We introduce a novel, simple method for learning SFs directly from pixels. Our approach uses a combination of a Temporal-difference (TD) loss and a reward prediction loss, which together capture the basic mathematical definition of SFs. We show that our approach matches or outperforms existing SF learning techniques in both 2D (Minigrid), 3D (Miniworld) mazes and Mujoco, for both single and continual learning scenarios. As well, our technique is efficient, and can reach higher levels of performance in less time than other approaches. Our work provides a new, streamlined technique for learning SFs directly from pixel observations, with no pretraining required.

2024-09-25

NeurIPS.cc/2024/Conference (poster)

Stochastic Wiring of Cell Types Enhances Fitness by Generating Phenotypic Variability

Divyansha Lachi

Ann Huang

Augustine N. Mavor-Parker

Anthony Zador

The development of neural connectivity is a crucial biological process that gives rise to diverse brain circuits and behaviors. Neural devel… (see more)opment is a stochastic process, but this stochasticity is often treated as a nuisance to overcome rather than as a functional advantage. Here we use a computational model, in which connection probabilities between discrete cell types are genetically specified, to investigate the benefits of stochasticity in the development of neural wiring. We show that this model can be viewed as a generalization of a powerful class of artificial neural networks—Bayesian neural networks—where each network parameter is a sample from a distribution. Our results reveal that stochasticity confers a greater benefit in large networks and variable environments, which may explain its role in organisms with larger brains. Surprisingly, we find that the average fitness over a population of agents is higher than a single agent defined by the average connection probability. Our model reveals how developmental stochasticity, by inducing a form of non-heritable phenotypic variability, can increase the probability that at least some individuals will survive in rapidly changing, unpredictable environments. Our results suggest how stochasticity may be an important feature rather than a bug in neural development.

2024-08-08

bioRxiv (preprint)

Synaptic Weight Distributions Depend on the Geometry of Plasticity

A growing literature in computational neuroscience leverages gradient descent and learning algorithms that approximate it to study synaptic … (see more)plasticity in the brain. However, the vast majority of this work ignores a critical underlying assumption: the choice of distance for synaptic changes - i.e. the geometry of synaptic plasticity. Gradient descent assumes that the distance is Euclidean, but many other distances are possible, and there is no reason that biology necessarily uses Euclidean geometry. Here, using the theoretical tools provided by mirror descent, we show that the distribution of synaptic weights will depend on the geometry of synaptic plasticity. We use these results to show that experimentally-observed log-normal weight distributions found in several brain areas are not consistent with standard gradient descent (i.e. a Euclidean geometry), but rather with non-Euclidean distances. Finally, we show that it should be possible to experimentally test for different synaptic geometries by comparing synaptic weight distributions before and after learning. Overall, our work shows that the current paradigm in theoretical work on synaptic plasticity that assumes Euclidean synaptic geometry may be misguided and that it should be possible to experimentally determine the true geometry of synaptic plasticity in the brain.

2024-01-16

ICLR.cc/2024/Conference (spotlight)

Addressing Sample Inefficiency in Multi-View Representation Learning

Kumar Krishna Agrawal

Shagun Sodhani

Adam M. Oberman

2024-01-01

NeurIPS (published)

Harnessing small projectors and multiple views for efficient vision pretraining

Kumar Krishna Agrawal

Shagun Sodhani

Adam M. Oberman

Recent progress in self-supervised (SSL) visual representation learning has led to the development of several different proposed frameworks … (see more)that rely on augmentations of images but use different loss functions. However, there are few theoretically grounded principles to guide practice, so practical implementation of each SSL framework requires several heuristics to achieve competitive performance. In this work, we build on recent analytical results to design practical recommendations for competitive and efficient SSL that are grounded in theory. Specifically, recent theory tells us that existing SSL frameworks are minimizing the same idealized loss, which is to learn features that best match the data similarity kernel defined by the augmentations used. We show how this idealized loss can be reformulated to a functionally equivalent loss that is more efficient to compute. We study the implicit bias of using gradient descent to minimize our reformulated loss function and find that using a stronger orthogonalization constraint with a reduced projector dimensionality should yield good representations. Furthermore, the theory tells us that approximating the reformulated loss should be improved by increasing the number of augmentations, and as such using multiple augmentations should lead to improved convergence. We empirically verify our findings on CIFAR, STL and Imagenet datasets, wherein we demonstrate an improved linear readout performance when training a ResNet-backbone using our theoretically grounded recommendations. Remarkably, we also demonstrate that by leveraging these insights, we can reduce the pretraining dataset size by up to 2

2023-12-17

ArXiv (preprint)

arxiv.org

On the Information Geometry of Vision Transformers

Sonia Joseph

Kumar Krishna Agrawal

2023-11-28

NeurIPS.cc/2023/Workshop/NeurReps (poster)

On the Varied Faces of Overparameterization in Supervised and Self-Supervised Learning

Matteo Gamba

Kumar Krishna Agrawal

Agrawal

Hossein Azizpour

Mårten Björkman

The quality of the representations learned by neural networks depends on several factors, including the loss function, learning algorithm, a… (see more)nd model architecture. In this work, we use information geometric measures to assess the representation quality in a principled manner. We demonstrate that the sensitivity of learned representations to input perturbations, measured by the spectral norm of the feature Jacobian, provides valuable information about downstream generalization. On the other hand, measuring the coefficient of spectral decay observed in the eigenspectrum of feature covariance provides insights into the global representation geometry. First, we empirically establish an equivalence between these notions of representation quality and show that they are inversely correlated. Second, our analysis reveals the varying roles that overparameterization plays in improving generalization. Unlike supervised learning, we observe that increasing model width leads to higher discriminability and less smoothness in the self-supervised regime. Furthermore, we report that there is no observable double descent phenomenon in SSL with non-contrastive objectives for commonly used parameterization regimes, which opens up new opportunities for tight asymptotic analysis. Taken together, our results provide a loss-aware characterization of the different role of overparameterization in supervised and self-supervised learning.

2023-11-28

NeurIPS.cc/2023/Workshop/NeurReps (poster)

The feature landscape of visual cortex

Rudi Tong

Ronan da Silva

James Wilsenach

Stuart Trenholm

Understanding computations in the visual system requires a characterization of the distinct feature preferences of neurons in different visu… (see more)al cortical areas. However, we know little about how feature preferences of neurons within a given area relate to that area’s role within the global organization of visual cortex. To address this, we recorded from thousands of neurons across six visual cortical areas in mouse and leveraged generative AI methods combined with closed-loop neuronal recordings to identify each neuron’s visual feature preference. First, we discovered that the mouse’s visual system is globally organized to encode features in a manner invariant to the types of image transformations induced by self-motion. Second, we found differences in the visual feature preferences of each area and that these differences generalized across animals. Finally, we observed that a given area’s collection of preferred stimuli (‘own-stimuli’) drive neurons from the same area more effectively through their dynamic range compared to preferred stimuli from other areas (‘other-stimuli’). As a result, feature preferences of neurons within an area are organized to maximally encode differences among own-stimuli while remaining insensitive to differences among other-stimuli. These results reveal how visual areas work together to efficiently encode information about the external world.

2023-11-05

bioRxiv (preprint)