Paper improves neural interaction modeling using nonlinear Hawkes processes.
problem Inability of classic Hawkes process to model inhibitory interactions.
method Augmented auxiliary latent variables and EM algorithm for efficient inference.
result Demonstrates accurate and efficient estimation of neural interaction dynamics.
Improved NiNo networks accelerate Adam training by up to 50%.
problem Accelerating neural network training with stable and efficient methods.
method Proposed NiNo networks that leverage neuron connectivity and graph neural networks to nowcast parameters periodically during Adam training.
result Accelerates Adam training by up to 50% in vision and language tasks.
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.
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)…
We present two Bayesian procedures to infer the interactions and external currents in an assembly of stochastic integrate-and-fire neurons from the recording of their spiking activity. The first procedure is based on the exact calculation of the most likely time courses of the neuron membrane potentials conditioned by …
In this study, we analyzed the activity of monkey V1 neurons responding to grating stimuli of different orientations using inference methods for a time-dependent Ising model. The method provides optimal estimation of time-dependent neural interactions with credible intervals according to the sequential Bayes estimation…
Neuron Shapley identifies key neurons in deep networks, improving model accuracy and fairness.
problem Identifying responsible neurons in deep networks for better model performance and fairness.
method Neuron Shapley framework quantifies neuron contributions, accounting for interactions.
result Removing just 30 critical filters can destroy model accuracy, revealing network function.
Massif helps interpret adversarial attacks on deep learning models.
problem Vulnerability of deep learning models to adversarial attacks.
method Interactive tool for visualizing and interpreting neurons affected by adversarial attacks.
result Massif provides a high-level overview and detailed low-level analysis of adversarial effects.
Deep neural networks (DNNs) are known for extracting useful information from large amounts of data. However, the representations learned in DNNs are typically hard to interpret, especially in dense layers. One crucial issue of the classical DNN model such as multilayer perceptron (MLP) is that neurons in the same layer…
This paper presents a Bayesian approach to learning the connectivity structure of a group of neurons from data on configuration frequencies. A major objective of the research is to provide statistical tools for detecting changes in firing patterns with changing stimuli. Our framework is not restricted to the well-under…
A new theory explains large associative memory with biological plausibility.
problem Large associative memory in neurobiology and machine learning.
method Microscopic theory with hidden neurons and two-body interactions.
result Valid model of large associative memory with biological plausibility.
New model explains visual illusions using sub-Riemannian geometry.
problem Mathematical modeling of Poggendorff-type visual illusions.
method Cortical-inspired sub-Riemannian model with sub-Laplacian evolution.
result Sub-Riemannian kernel enhances visual misperceptions and biases.
New method for online learning in interacting particle systems.
problem Parameter estimation in stochastic interacting particle systems.
method Stochastic approximation of gradient of asymptotic log likelihood using continuous observations.
result Convergence to stationary points of asymptotic log-likelihood under suitable assumptions.
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…
This study explains how adversarial interaction creates non-homogeneous patterns using a pseudo-Reaction-Diffusion model.
problem Understanding how adversarial interaction leads to non-homogeneous patterns in systems.
method Developed a pseudo-Reaction-Diffusion model to explain the mechanism.
result Turing instability is involved in creating non-homogeneous patterns.
A dynamical neural network consists of a set of interconnected neurons that interact over time continuously. It can exhibit computational properties in the sense that the dynamical system's evolution and/or limit points in the associated state space can correspond to numerical solutions to certain mathematical optimiza…
BDH model learns like the brain, rivaling Transformer performance.
problem Leveraging brain-like properties for machine learning.
method Scale-free biologically inspired network of neuron particles.
result BDH model achieves Transformer-like performance with interpretability.
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.
Neural networks are based on a simplified model of the brain. In this project, we wanted to relax the simplifying assumptions of a traditional neural network by making a model that more closely emulates the low level interactions of neurons. Like in an RNN, our model has a state that persists between time steps, so tha…
Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform. This leads either to an inefficient distribution of computational resources or an extensive increase in the comput…
CREIMBO models diverse brain activity by identifying hidden neural sub-circuits and their non-stationary interactions.
problem Lack of alignment in neural recordings limits analysis of brain-wide dynamics.
method CREIMBO learns a unified model of neural dynamics by assuming multiple hidden global sub-circuits representing ensemble interactions.
result CREIMBO discovers session-specific neural ensembles and their non-stationary interactions, revealing cross-subject neural mechanisms.
Identification of patterns from discrete data time-series for statistical inference, threat detection, social opinion dynamics, brain activity prediction has received recent momentum. In addition to the huge data size, the associated challenges are, for example, (i) missing data to construct a closed time-varying compl…
GraphDINO learns neuronal morphologies from unlabeled data.
problem Unsupervised learning of neuronal morphologies from unlabeled data.
method Transformer-based approach with novel attention mechanism and data augmentation.
result GraphDINO yields morphological clusterings on par with expert classification.
Novel approach constructs differential causal networks from EEG data.
problem Difficulty in modeling interactions of thousands of neurons in group comparisons.
method Hierarchical differential dynamic causal nets based on Chen-Fliess expansions.
result Evidence of network functional disruptions in epileptic brains.
Developing electrophysiological recordings of brain neuronal activity and their analysis provide a basis for exploring the structure of brain function and nervous system investigation. The recorded signals are typically a combination of spikes and noise. High amounts of background noise and possibility of electric sign…
Paper introduces supervised and unsupervised TAM models for binary neurons.
problem Learning and retrieval of structured triplets of patterns in neural networks.
method Extends Hebbian paradigm to supervised and unsupervised protocols, using glassy statistical mechanical techniques.
result Obtained self-consistency equations for critical dataset sizes and retrieval performance.
Improves neural network verification by merging abstract domains and Lagrangian methods.
problem Prove provable bounds for neural network outputs given input ranges.
method Uses zonotopes within a Lagrangian decomposition to verify deep neural networks.
result Yields bounds that improve upon existing techniques in both time and tightness.
Captum library simplifies model interpretability for PyTorch.
problem Improving model interpretability for various PyTorch models.
method Unified, open-source library with generic attribution algorithms and metrics.
result Unified and scalable model interpretability for multimodal inputs.
Model detects patterns in noisy binary data, explaining neuron activity in terms of cell assemblies.
problem Detecting structure in noisy or approximate repeats of patterns in sparse binary data.
method Probabilistic binary latent variable model based on Noisy-OR model, inferring sparse activity in latent variables.
result Model successfully extracts and explains latent structure in spiking neural data.
Analyzes minima of deep linear networks with weight decay.
problem Understanding the loss landscape of deep neural networks.
method Analytical solutions for global minima with weight decay and stochastic neurons.
result The origin is a special point with qualitatively different minima in networks with more than 1 hidden layer.
REPAIR mitigates variance collapse to enable linear interpolation between SGD solutions.
problem Linear interpolation between SGD solutions is difficult due to variance collapse in permuted activations.
method REPAIR rescales preactivations of interpolated networks to mitigate variance collapse.
result 60%-100% relative barrier reduction across various architectures and tasks.
Estimates nonlinear Hawkes processes using RKHSs with ReLU rectification.
problem Nonlinear multivariate Hawkes processes with complex interaction functions.
method Nonparametric estimation using RKHSs with approximations for ReLU and integral operators.
result Proposes an estimation method with bounds on approximation errors.
Experiments that study neural encoding of stimuli at the level of individual neurons typically choose a small set of features present in the world --- contrast and luminance for vision, pitch and intensity for sound --- and assemble a stimulus set that systematically varies along these dimensions. Subsequent analysis o…
Accurate statistical models of neural spike responses can characterize the information carried by neural populations. But the limited samples of spike counts during recording usually result in model overfitting. Besides, current models assume spike counts to be Poisson-distributed, which ignores the fact that many neur…
Studying neural connectivity is considered one of the most promising and challenging areas of modern neuroscience. The underpinnings of cognition are hidden in the way neurons interact with each other. However, our experimental methods of studying real neural connections at a microscopic level are still arduous and cos…
New method improves graph neural networks by considering different types of relations in sampling.
problem Current graph neural networks ignore relation types in biomedical graphs, leading to suboptimal performance.
method Proposes relation-dependent sampling for multi-relational graphs to balance relation frequency and importance.
result State-of-the-art graph neural networks achieve better accuracy and efficiency with relation-dependent sampling.
Estimates log-likelihood of interacting particle systems using virtual particles.
problem Inconsistent estimation of finite-particle log-likelihood in large particle systems.
method Stochastic gradient estimate using continuous trajectory and virtual particle systems.
result Convergence to stationary points of limiting mean-field system's log-likelihood.
A new method uncovers discrete and continuous factors in gene expression data.
problem Jointly identifying discrete and continuous factors of variability without supervision.
method cpl-mixVAE framework using multiple interacting networks.
result The method successfully uncovers discrete and continuous factors in gene expression data.
Study shows how SGD in large neural networks behaves as neurons increase.
problem Understanding SGD behavior in overparameterized neural networks.
method Probabilistic approach to continuous-time dynamics of SGD, focusing on particle interactions.
result Particles' interactions asymptotically vanish, leading to a mean-field limit.
This work analyzes how different forms of compressibility affect adversarial robustness in neural networks.
problem Understanding the interaction between compressibility and adversarial robustness in neural networks.
method Developed a principled framework to analyze the effects of neuron-level sparsity and spectral compressibility on adversarial robustness.
result Identified that different forms of compression can induce highly sensitive directions in the representation space that adversaries can exploit.
Proposes a new method to better understand complex system interactions.
problem Current methods like Granger causality and transfer entropy fail to capture higher-order interactions.
method Introduces a generalized approach to capture multivariate causal interactions.
result The method can distinguish causal roles in synergetic interactions.
Much of studies on neural computation are based on network models of static neurons that produce analog output, despite the fact that information processing in the brain is predominantly carried out by dynamic neurons that produce discrete pulses called spikes. Research in spike-based computation has been impeded by th…
3-layer NTK models generalize better than 2-layer models, especially with large input dimensions.
problem Understanding the generalization of overparameterized neural networks.
method Analyzing the 3-layer NTK model's test error and comparing it to 2-layer NTK models.
result 3-layer NTK models have a faster descent in test error with respect to the number of neurons in the second hidden layer.
Describes explaining neurons in deep representations using compositional logical concepts.
problem Interpreting neuron behavior in deep neural networks.
method Identifying compositional logical concepts that closely approximate neuron behavior.
result Compositional explanations provide insights into model performance and allow for adversarial example creation.
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.
Under-parameterized networks can either copy or average teacher weights, leading to universal optimal solutions.
problem Approximating a teacher network with an under-parameterized student network.
method Analyzing shallow neural networks with erf activation function and unitary teacher weights, proving copy-average configurations are critical points and finding the optimal solution.
result The optimal solution for under-parameterized networks has a universal structure, whether copying or averaging teacher neurons.
Many iterative and non-iterative methods have been developed for inverse problems associated with Ising models. Aiming to derive an accurate non-iterative method for the inverse problems, we employ the tree-reweighted approximation. Using the tree-reweighted approximation, we can optimize the rigorous lower bound of th…
In this paper we provide a comprehensive analysis of a structural model for the dynamics of prices of assets traded in a market originally proposed in [1]. The model takes the form of an interacting generalization of the geometric Brownian motion model. It is formally equivalent to a model describing the stochastic dyn…