Arna Ghosh

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… (voir plus)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 (prépublication)

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 … (voir plus)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 (publié)

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 … (voir plus)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 (prépublication)

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… (voir plus)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… (voir plus)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 (prépublication)

Learning better with Dale’s Law: A Spectral Perspective

How gradient estimator variance and bias impact learning in neural networks

Yuhan Helena Liu

Guillaume Lajoie

Konrad Paul Kording

There is growing interest in understanding how real brains may approximate gradients and how gradients can be used to train neuromorphic chi… (voir plus)ps. However, neither real brains nor neuromorphic chips can perfectly follow the loss gradient, so parameter updates would necessarily use gradient estimators that have some variance and/or bias. Therefore, there is a need to understand better how variance and bias in gradient estimators impact learning dependent on network and task properties. Here, we show that variance and bias can impair learning on the training data, but some degree of variance and bias in a gradient estimator can be beneficial for generalization. We find that the ideal amount of variance and bias in a gradient estimator are dependent on several properties of the network and task: the size and activity sparsity of the network, the norm of the gradient, and the curvature of the loss landscape. As such, whether considering biologically-plausible learning algorithms or algorithms for training neuromorphic chips, researchers can analyze these properties to determine whether their approximation to gradient descent will be effective for learning given their network and task properties.

2023-02-01

ICLR.cc/2023/Conference (poster)

H OW GRADIENT ESTIMATOR VARIANCE AND BIAS COULD IMPACT LEARNING IN NEURAL CIRCUITS

Yuhan Helena Liu

Guillaume Lajoie

Konrad K¨ording

There is growing interest in understanding how real brains may approximate gradients and how gradients can be used to train neuromorphic chi… (voir plus)ps. However, neither real brains nor neuromorphic chips can perfectly follow the loss gradient, so parameter updates would necessarily use gradient estimators that have some variance and/or bias. Therefore, there is a need to understand better how variance and bias in gradient estimators impact learning dependent on network and task properties. Here, we show that variance and bias can impair learning on the training data, but some degree of variance and bias in a gradient estimator can be beneficial for generalization. We find that the ideal amount of variance and bias in a gradient estimator are dependent on several properties of the network and task: the size and activity sparsity of the network, the norm of the gradient, and the curvature of the loss landscape. As such, whether considering biologically-plausible learning algorithms or algorithms for training neuromorphic chips, researchers can analyze these properties to determine whether their approximation to gradient descent will be effective for learning given their network and task properties.

2023-01-01

(publié)

www.semanticscholar.org

Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece

Luke Y. Prince

Roy Henha Eyono

Ellen Boven

Joseph Pemberton

Franz Scherr

Claudia Clopath

Rui Ponte Costa

Wolfgang Maass

Cristina Savin

Katharina Wilmes

We provide a brief review of the common assumptions about biological learning with findings from experimental neuroscience and contrast them… (voir plus) with the efficiency of gradient-based learning in recurrent neural networks. The key issues discussed in this review include: synaptic plasticity, neural circuits, theory-experiment divide, and objective functions. We conclude with recommendations for both theoretical and experimental neuroscientists when designing new studies that could help bring clarity to these issues.

2022-04-27

Neurons, Behavior, Data analysis, and Theory (publié)