Single spiking neuron outperforms ConvNets in counting weakly labeled concepts.
problem Counting weakly labeled concepts in MNIST task.
method Improved gradient-based local learning rule for leaky integrate and fire model.
result Single spiking neuron outperforms conventional ConvNets in MNIST counting task.
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…
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.
Deep neural networks can approximate natural functions with fewer neurons than shallower networks.
problem Understanding the expressibility of neural networks in approximating natural functions.
method Analyzing the neuron requirements for approximating natural multivariate polynomials with deep and shallow networks.
result The neuron requirement for deep networks grows linearly with the number of variables, while shallow networks require exponentially more neurons.
New training method for ReLU networks achieves optimal weight size for memorization.
problem Approximate memorization of arbitrary real labels with neural networks.
method Complex recombination training procedure for ReLU networks.
result Approximate memorization with nearly optimal weight size and neuron count.
Novel 'strong neuron' improves deep learning efficiency and robustness.
problem Improving deep learning efficiency and robustness against adversarial attacks.
method Introducing a novel 'strong neuron' model and a constructive training algorithm.
result Achieved 10x-100x reduction in operations count and hardware requirements.
A new SNN model explains decision-making with learning and spiking neurons.
problem Lack of learning mechanism in existing models for decision-making.
method Proposes a Spiking Neural Network (SNN) model that incorporates a learning mechanism and uses multivariate Hawkes processes.
result Shows a coupling between DDM and Poisson counter models and derives a DDM from a Hawkes network of spiking neurons.
Spark Transformer achieves high sparsity in FFN and attention without sacrificing model quality.
problem Inactivity of most neurons in FFN of Transformers, leading to inefficiency.
method Top-k masking, statistical top-k algorithm, and predictor for activated entries.
result Only 8% of FFN neurons are activated, achieving up to 2.5x wall-time speedup.
We develop a fast inference method for non-conjugate Gaussian process models on spike count data.
problem Non-Gaussian spike count data complicates Gaussian Process Factor Analysis.
method We introduce Polynomial Approximate Log-Likelihood (PAL) estimators for non-conjugate GPFA models.
result PAL estimators achieve fast and accurate extraction of latent structure from spike train data.
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…
NegBio-VAE models neural spike counts with negative binomial distribution.
problem Limited biological plausibility of continuous latent variables in VAEs for neural spike modeling.
method Proposes a negative binomial latent-variable model with a dispersion parameter for overdispersed spike count modeling.
result NegBio-VAE outperforms competing models in reconstruction and generation tasks.
New CUSUM method detects changes in Hawkes networks efficiently.
problem Detecting abrupt changes in Hawkes networks.
method Efficient online recursive implementation of CUSUM statistic.
result Proposed CUSUM method outperforms existing methods.
Develops a new neural spike train decoding framework using topological data.
problem Decoding neural spike trains from head direction and grid cells.
method Combines simplicial complex discovery with deep learning to capture higher-order connectivity.
result Demonstrates effectiveness on head direction and trajectory prediction datasets.
Study on the complexity of deep neural networks and their linear regions.
problem Understanding the complexity and structure of deep neural networks.
method Leveraging the dimension of the space defining each linear region, the study presents bounds and methods for counting linear regions.
result Tighter upper and lower bounds for the maximum number of linear regions on rectifier networks, and a method for exact enumeration.
Improved neural network training by coupled initialization reduces neuron count.
problem Training neural networks efficiently with fewer neurons.
method Coupled initialization of weights into pairs of identical Gaussian vectors.
result Significantly reduced number of neurons required for network convergence.
Deep learning predicts traffic flow on Sydney motorways.
problem Challenging traffic flow prediction due to inter-dependencies.
method Advanced deep learning framework using CNN-LSTM.
result Deep learning models outperform traditional methods.
This study uses neural networks to solve interpolation problems with sparse, infinitely wide layers.
problem Exact data interpolation using sparse, infinitely wide neural networks.
method Atomic norm framework to derive convex hulls and equivalent convex formulations.
result Simple characterizations of convex hulls for different constraints on network weights and biases.
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.
New q-neurons improve neural network performance.
problem Improving neural network activation functions.
method Introducing q-neurons based on Jackson's q-derivatives with stochastic parameters. result Consistently improved performance over state-of-the-art activation functions.
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.
This research investigates selectively pruning hyper and hypo neurons to improve neural network generalization.
problem Improving neural network generalization to unseen data.
method Investigates pruning hyper and hypo neurons selectively in fully connected layers of CNNs.
result Selective pruning of hyper and hypo neurons improves model performance on out-of-domain data.
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.
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.
Sparse neural networks trained on commodity hardware achieve high accuracy for high-dimensional data.
problem Training and deploying modern ANNs on commodity hardware due to model size and data volume challenges.
method Introducing a technique to train truly sparse neural networks with fixed parameter count throughout training.
result Achieved higher accuracy than traditional methods and trained models with over 1 million neurons on a typical laptop.
Developed a BP algorithm for training neural networks with 2nd order neurons.
problem Training neural networks with nonlinear quadratic operations.
method Created a general backpropagation algorithm.
result Validated the generalized BP algorithm through numerical studies.
Quadratic autoencoder improves low-dose CT image denoising.
problem Low-dose CT image denoising.
method Quadratic autoencoder architecture applied to CT denoising.
result Quadratic autoencoder achieves superior denoising performance and efficiency.
Solves internal covariate shift and dying neurons with linked neurons.
problem Internal covariate shift and dying neurons in deep learning.
method Defining linked neurons with two constraints: shared operating point and non-zero gradient.
result Linked neurons effectively solve internal covariate shift and improve training efficiency.
Neural network robustness evaluated in the presence of failing neurons.
problem Evaluating robustness of neural networks in the face of neuron failures.
method Leveraging Lipschitz continuity of activation functions, calculating Forward Error Propagation.
result Tight bounds on the number of failing neurons before network accuracy is compromised.
We developed a faster method for calculating neuron importance in neural networks.
problem Assigning importance to individual neurons in deep learning models.
method We developed Neuron Integrated Gradients, a scalable implementation of Total Conductance.
result Neuron Integrated Gradients is faster and empirically stronger than DeepLIFT.
BEAN models neuronal correlations to create interpretable representations.
problem Hard interpretation of dense-layer representations in DNNs.
method Inspired by neuroscience, BEAN models neuronal correlations and dependencies.
result BEAN enables formation of interpretable neuronal clusters without sacrificing model performance.
The number of linear regions in neural networks is far below exponential, even after training.
problem Understanding the expressivity of neural networks, especially those with ReLU activation.
method Mathematical framework to count linear regions and measure their boundaries, analyzing networks at initialization and after training.
result The average number of regions along any one-dimensional subspace grows linearly in the total number of neurons, not exponentially.
SpaRCe optimizes reservoir computing by learning neuron thresholds to improve performance and prevent forgetting.
problem Improving performance and preventing forgetting in reservoir computing networks.
method Integrates neuron-specific learnable thresholds to optimize sparsity without altering dynamics, learning read-out weights and thresholds via gradient rule.
result Threshold learning improves performance and alleviates catastrophic forgetting.
It will be shown that according to theorems of K. Menger, every neuron grid if identified with a curve is able to preserve the adopted qualitative structure of a data space. Furthermore, if this identification is made, the neuron grid structure can always be mapped to a subset of a universal neuron grid which is constr…
This work improves DNN interpretability by reducing neuron ambiguity.
problem Lack of interpretability in DNNs, especially in healthcare applications.
method Developed a metric to evaluate neuron consistency, used adversarial examples to identify ambiguous features, and proposed adversarial training to improve consistency.
result Reduced ambiguity of neurons in DNNs, improving interpretability.
A new method to understand neural networks by sampling the 'inverse set' of a neuron.
problem Understanding the internal representation of neurons in neural networks.
method Optimization-based sampling approach to characterize the input space that excites a neuron.
result Inspection of samples reveals regularities that help understand the neuron's representation.
CHANI learns classification tasks with local transformations inspired by biology.
problem Proving neural networks can learn classification tasks with local transformations.
method CHANI uses spiking neurons modeled by Hawkes processes with expert aggregation for local learning.
result CHANI can learn and encode multiple classes, forming assemblies of neurons.
BinaryGAN uses binary neurons for GAN training.
problem Training GANs with binary outputs.
method End-to-end backpropagation with sigmoid-adjusted straight-through estimators.
result BinaryGAN can generate binary-valued predictions.
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.
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.
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. …
Stable unactivated neurons reduce expressiveness in ReLU networks.
problem Reducing expressiveness in ReLU neural networks due to stably unactivated neurons.
method Investigated the probability of neurons being stably unactivated in ReLU networks with symmetric weight and bias distributions.
result Proved the probability of a neuron being stably unactivated in the second hidden layer of a ReLU network.
Novel chaotic neurons improve AI with minimal training data.
problem Limited training data for AI algorithms.
method Intrinsically chaotic neurons inspired by chaos theory.
result Classification accuracy up to 95.8% with just 2 training samples per class.
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.
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.
New neuron model learns and adapts its receptive field.
problem Learning and focusing on informative inputs.
method Adaptive locally connected neuron model using backpropagation.
result Focusing neurons outperform dense layers in classification tasks.
Deep CNN model predicts neuronal cell health from images.
problem Predicting the biological activity of chemical compounds on neuronal cells.
method Deep convolutional neural network (CNN) with residual connections.
result Achieved 99.6% accuracy in distinguishing treated from untreated cells.