Gradient descent struggles with learning a single neuron with bias.
problem Learning a single neuron with a bias term in the realizable setting with ReLU activation.
method Theoretical study using gradient descent, characterizing critical points, and providing convergence guarantees.
result Gradient descent faces significant challenges in learning a single neuron with bias, unlike the bias-less case.
Single-spike neurons can approximate as well as multi-spike neurons.
problem Limitation of single-spike neurons in spiking neural networks.
method Comparison of single-spike and multi-spike neural networks.
result Single-spike and multi-spike neural networks are equivalent in approximation capabilities.
Single ReLU neuron's gradient dynamics reveal support vectors as key to generalization.
problem Understanding the generalization capability of ReLU networks.
method Examined gradient flow dynamics and support vectors in single ReLU neuron training.
result Support vectors play a crucial role in the generalization of ReLU networks.
To understand how rich dynamics emerge in neural populations, we require models exhibiting a wide range of activity patterns while remaining interpretable in terms of connectivity and single-neuron dynamics. However, it has been challenging to fit such mechanistic spiking networks at the single neuron scale to empirica…
Recent advances in neuroscience have revealed many principles about neural processing. In particular, many biological systems were found to reconfigure/recruit single neurons to generate multiple kinds of decisions. Such findings have the potential to advance our understanding of the design and optimization process of …
Over-parametrization speeds up learning a single neuron model.
problem Understanding why over-parametrization accelerates learning in neural networks.
method Studied a simple model of a single teacher neuron with quadratic activation, showing how over-parametrization can lead to faster convergence.
result Over-parametrization helps gradient descent enter the neighborhood of a global optimal solution faster.
Efficiently learns a single neuron with adversarial noise, improving on prior work.
problem Learning a single neuron with adversarial label noise.
method Efficient algorithm using local error bounds from optimization theory.
result Approximates optimal L22-error within a constant factor. Simplified neural network EFTs reveal a single critical condition.
problem Understanding neuron statistics in neural networks at initialization.
method Diagrammatic approach to effective field theories (EFTs).
result A single condition governs criticality of all neuron preactivations.
Topological methods improve neuron analysis and tracer injection summary.
problem Traditional methods fail to capture the tree-like structure of neurons.
method Discrete Morse (DM) Theory for neuron skeletonization and consensus tree summarization.
result Significant performance improvements over non-topological methods.
Single neuron learns predictive uncertainty in deep learning models.
problem Uncertainty estimation in deep learning models, especially with respect to model specification and training procedure.
method Introduces a non-parametric quantile estimation method using a single neuron.
result The method achieves competitive predictive uncertainty quantification quality and coverage compared to state-of-the-art solutions.
Single neuron with ADA learns XOR and outperforms other functions.
problem Classifying linearly non-separable data.
method Proposed a new artificial neuron with apical dendrite activation.
result ADA function achieves 100% accuracy on XOR and superior performance on benchmark datasets.
Single neuron sensitivity reveals model weaknesses.
problem Understanding model susceptibility to adversarial attacks.
method Analyzing sensitivity of individual neurons to perturbations.
result Single neuron attacks are as effective as full model attacks.
Gradient descent slows significantly in over-parameterized single neuron learning.
problem Learning a single neuron with over-parameterization and square loss.
method Analysis of gradient descent dynamics, proving convergence rates and lower bounds.
result Over-parameterization can exponentially slow down the convergence rate of gradient descent.
SeReNe prunes neurons with low sensitivity to reduce network size.
problem Large neural networks consume too many resources on resource-constrained devices.
method Exploits neural sensitivity as a regularizer to prune neurons with low sensitivity.
result Pruning neurons with low sensitivity achieves competitive compression ratios.
The artificial neural network is a popular framework in machine learning. To empower individual neurons, we recently suggested that the current type of neurons could be upgraded to 2nd order counterparts, in which the linear operation between inputs to a neuron and the associated weights is replaced with a nonlinear qu…
Cataloging the neuronal cell types that comprise circuitry of individual brain regions is a major goal of modern neuroscience and the BRAIN initiative. Single-cell RNA sequencing can now be used to measure the gene expression profiles of individual neurons and to categorize neurons based on their gene expression profil…
Neurons in cortical circuits exhibit coordinated spiking activity, and can produce correlated synchronous spikes during behavior and cognition. We recently developed a method for estimating the dynamics of correlated ensemble activity by combining a model of simultaneous neuronal interactions (e.g., a spin-glass model)…
Modeling hidden neurons in SNNs using mesoscopic approximations.
problem Underconstrained problem of modeling unobserved neurons in SNNs.
method Coarse-graining and mean-field approximations to derive neuLVM.
result neuLVM can efficiently model large SNNs and recover connectivity parameters.
Gradient descent learns a single neuron without knowing the relationship between inputs and labels.
problem Learning a single neuron without knowing the relationship between inputs and labels.
method Using gradient descent to minimize empirical risk over i.i.d. samples, with a nonconvex and nonsmooth optimization problem.
result Gradient descent achieves near-optimal population risk in polynomial time and sample complexity.
Mechanistic models of single-neuron dynamics have been extensively studied in computational neuroscience. However, identifying which models can quantitatively reproduce empirically measured data has been challenging. We propose to overcome this limitation by using likelihood-free inference approaches (also known as App…
Despite our extensive knowledge of biophysical properties of neurons, there is no commonly accepted algorithmic theory of neuronal function. Here we explore the hypothesis that single-layer neuronal networks perform online symmetric nonnegative matrix factorization (SNMF) of the similarity matrix of the streamed data. …
Understanding the morphological changes of primary neuronal cells induced by chemical compounds is essential for drug discovery. Using the data from a single high-throughput imaging assay, a classification model for predicting the biological activity of candidate compounds was introduced. The image recognition model wh…
A new neural network model using weighted Lehmer means and multiplets.
problem Creating a neural network that can emulate different generalized mean cases.
method Replacing dot product with weighted Lehmer mean and using multiplets of neurons.
result The network can emulate the exclusive-or problem and approximate functions.
Neural networks learn to mimic brain neurons with two-input activation functions, improving performance and robustness.
problem Training neural networks to mimic the complex interactions of brain neurons.
method Developed a network-in-network architecture with two-input activation functions, optimized hyperparameters, and compared to conventional ReLU networks.
result Two-input activation functions can learn soft XOR functions, improving network performance and robustness.
Single gradient step finds adversarial examples in random neural networks.
problem Finding adversarial examples in neural networks with random architectures.
method Gradient descent approach applied to random undercomplete and overcomplete two-layers neural networks.
result A single gradient step is sufficient to find adversarial examples in random neural networks.
DNPUs improve neural network performance with high-capacity nanoelectronic nodes.
problem Limited performance of single DNPUs in solving complex classification problems.
method Developed DNPUs as high-capacity neurons and implemented multi-DNPU networks.
result Feed-forward DNPU networks improve single DNPU performance from 77% to 94% test accuracy.
Study learns a neuron with non-monotonic activation functions.
problem Learning a single neuron with non-monotonic activation functions.
method Gradient descent (GD) with conditions on activation function and input distribution.
result Learnability of non-monotonic activation functions is established without monotonicity assumption.
We consider the fundamental problem of learning a single neuron x↦σ(w⊤x) using standard gradient methods. As opposed to previous works, which considered specific (and not always realistic) input distributions and activation functions σ(⋅), we ask whether a more general result is attainable, under mi…
Optimal neuron activation functions improve neural network performance.
problem Limited expressive power of standard neuron activation functions in neural networks.
method Additive Gaussian process regression to construct individual neuron activation functions.
result Optimal neuron activation functions lead to better performance and reduced overfitting.
The seemingly stochastic transient dynamics of neocortical circuits observed in vivo have been hypothesized to represent a signature of ongoing stochastic inference. In vitro neurons, on the other hand, exhibit a highly deterministic response to various types of stimulation. We show that an ensemble of deterministic le…
Given a length n sample from Rd and a neural network with a fixed architecture with W weights, k neurons, linear threshold activation functions, and binary outputs on each neuron, we study the problem of uniformly sampling from all possible labelings on the sample corresponding to different choices of…
Researchers develop methods to learn neuron dynamics from colored noise.
problem Learning nonlocal stochastic neuron dynamics from colored noise.
method Proposed two methods for closing Fokker-Planck equations: nonlocal large-eddy-diffusivity closure and data-driven sparse regression.
result Mutual information and total correlation between stimulus and neuron states calculated for FHN neuron.
Paper uses deep Ritz method for solving stationary Schrödinger equation, proving convergence and feature emergence.
problem Solving stationary Schrödinger equation with high-dimensional features.
method Deep Ritz method, gradient descent, single-index model, two-neuron model.
result Gradient descent converges to near-optimal solution, feature emergence observed in two-neuron model.
New method improves neural network verification by considering multivariate input space of ReLU neurons.
problem Improving the effectiveness of neural network verification algorithms.
method A new tightened convex relaxation for ReLU neurons considering multivariate input space.
result Our convex relaxation is significantly stronger than the commonly used univariate-input relaxation.
Probabilistic bounds on neuron death in deep networks, showing depth can be increased indefinitely.
problem Understanding neuron death in deep rectifier networks and its impact on model trainability.
method Deriving upper and lower bounds on neuron death probability as a function of model hyperparameters.
result The probability of neuron death decreases as network depth increases, provided width increases proportionally.
New metric captures individual neuron tuning across neural networks.
problem Need a metric that respects individual neuron tuning across different neural networks.
method Derived a 'soft' permutation-based metric using optimal transport theory.
result Metric avoids counter-intuitive outcomes and captures geometric insights.
Mixed integer programming identifies critical neurons in neural networks.
problem Identifying neurons critical for network performance and generalization.
method Developed a mixed integer program (MIP) to assign importance scores to neurons, guiding pruning decisions.
result The method identifies multiple 'lucky' sub-networks resulting in optimized architectures that generalize across datasets.
Study shows SQ lower bounds for learning ReLUs with Massart noise.
problem Learning a single neuron in the presence of Massart noise.
method Statistical Query (SQ) lower bounds for efficient learning algorithms.
result No efficient SQ algorithm can approximate the optimal error within any constant factor.
Recent developments in high throughput profiling of individual neurons have spurred data driven exploration of the idea that there exist natural groupings of neurons referred to as cell types. The promise of this idea is that the immense complexity of brain circuits can be reduced, and effectively studied by means of i…
Optimization geometry affects deep learning performance.
problem The impact of optimization geometry on deep learning performance.
method Analysis of pseudogradient methods for learning generalized linear models.
result Non-asymptotic bounds on generalization error characterize model performance.
Recent advancements in language representation models such as BERT have led to a rapid improvement in numerous natural language processing tasks. However, language models usually consist of a few hundred million trainable parameters with embedding space distributed across multiple layers, thus making them challenging t…
A measure of neural complexity quantifies how hard it is to access information across neurons.
problem Understanding how mutual information is distributed among neurons in neural networks.
method Partial Information Decomposition (PID) to disentangle contributions of single neurons, multiple neurons, and synergistic effects.
result Representational Complexity measures the difficulty of accessing information across multiple neurons.
Neurons and networks in the cerebral cortex must operate reliably despite multiple sources of noise. To evaluate the impact of both input and output noise, we determine the robustness of single-neuron stimulus selective responses, as well as the robustness of attractor states of networks of neurons performing memory ta…
Automated method finds meaningful directions in neural network activations.
problem Mixed selectivity in neurons makes interpretation challenging.
method Automated quantification of interpretability and discovery of meaningful directions.
result Meaningful directions in neural network activations are more interpretable than individual neurons.
We show that a collection of Gaussian mixture models (GMMs) in Rn can be optimally classified using O(n) neurons in a neural network with two hidden layers (deep neural network), whereas in contrast, a neural network with a single hidden layer (shallow neural network) would require at least O(exp(n)) neurons …
Partial fusion combines neural networks to balance accuracy and efficiency.
problem Balancing accuracy and computational cost in neural networks.
method Extending weight aggregation methods based on neuron-level similarity, using partial optimal transport to match similar neurons.
result Achieves a flexible tradeoff between computational cost and performance.
Algorithm learns a single neuron robustly to shifts and adversarial noise.
problem Learning a single neuron robustly to distributional shifts and adversarial label noise.
method Designs a computationally efficient algorithm using primal-dual framework.
result Recover a vector satisfying a risk bound under adversarial conditions.
Study on how noise and variation-norm regularisation help shallow ReLU networks use fewer neurons.
problem Understanding how shallow ReLU networks use a finite number of neurons in the infinitely wide limit.
method Analysis of two regularisation strategies: noise injection and variation-norm.
result Both regularisation methods minimize functions with a finite number of neurons, regardless of overparametrisation.