The study explains delayed spikes in batch-normalized models.
problem Delayed spikes in batch-normalized models.
method Analyzing batch-normalized linear models, deriving conditions for delayed onset and waiting time.
result Explicit conditions for delayed-onset and waiting time in whitened square-loss linear regression.
This paper explains how low-precision arithmetic causes loss spikes in deep learning models.
problem Loss spikes during long-term training of deep neural networks.
method Analyzes the impact of floating-point precision limits on gradient updates and feature means.
result Numerical Feature Inflation (NFI) explains loss spikes and rapid parameter norm growth.
Stable GFlowNets prevent loss spikes and mode collapse in training.
problem Unstable training of GFlowNets leading to loss spikes and mode collapse.
method Assessed sensitivity of GFlowNet objectives, derived loss-to-TV bounds, and proposed Stable GFlowNets.
result Stable GFlowNets improve training behavior and distributional fidelity.
The paper explains spikes in training loss as catapults, improving feature learning and generalization.
problem Understanding and improving the training process of neural networks.
method Analysis of training loss spikes in SGD, empirical evidence of catapults, and demonstration of AGOP alignment.
result Catapults in training loss promote feature learning and better generalization.
New method converts conventional ANNs to SNNs with minimal loss and efficiency.
problem Difficulty in training SNNs directly from conventional ANNs due to discreteness.
method Proposes a novel pipeline combining threshold balance and soft-reset mechanisms for efficient conversion.
result Achieves almost no accuracy loss with only 1/10 of typical SNN simulation time.
Spiking neural networks (SNNs) offer a promising alternative to current artificial neural networks to enable low-power event-driven neuromorphic hardware. Spike-based neuromorphic applications require processing and extracting meaningful information from spatio-temporal data, represented as series of spike trains over …
Sleep-based regularization stabilizes STDP in recurrent neural networks.
problem Pathological weight dynamics in recurrent SNNs.
method Periodic offline phases with stochastic decay and spontaneous activity.
result Sleep-based renormalization prevents weight saturation and preserves learned structure.
In this work we analyse quantitatively the interplay between the loss landscape and performance of descent algorithms in a prototypical inference problem, the spiked matrix-tensor model. We study a loss function that is the negative log-likelihood of the model. We analyse the number of local minima at a fixed distance …
A high-parallelism SNN improves feature learning efficiency and robustness.
problem Slow learning speed and limited learning capability in existing SNNs.
method Inspired by Inception modules, high-parallelism architecture, Vote-for-All decoding, adaptive repolarization mechanism.
result Superior performance and competitive accuracy compared to state-of-the-art unsupervised SNNs.
Improved VB algorithm for high-dimensional logistic regression with theoretical guarantees.
problem Sparse high-dimensional logistic regression model selection.
method Spike and slab variational Bayes approximation.
result Optimal convergence rates in ℓ2 and prediction loss for sparse truths. Framework for training stochastic spiking neural networks with rough signals.
problem Training stochastic spiking neural networks with noisy spike timing and dynamics.
method Rough path theory and signature kernels for gradient computation.
result Pathwise gradients of SSNNs' trajectories and event times exist and satisfy a recursive relation.
Deep convolutional neural networks (CNNs) have shown great potential for numerous real-world machine learning applications, but performing inference in large CNNs in real-time remains a challenge. We have previously demonstrated that traditional CNNs can be converted into deep spiking neural networks (SNNs), which exhi…
Estimates neuronal connectivity from spike times using flexible Hawkes processes.
problem Learning latent network structure from multivariate point process data.
method Proposes a new nonstationary Hawkes process and uses sparse least squares estimation.
result Establishes non-asymptotic error bounds and selection consistency for estimated parameters.
Study shows how specialized attention circuits emerge during transformer training.
problem Understanding the mechanisms of transformer training dynamics at large scales.
method Controlled sparse modular addition task; monitoring token evolution via visual sandbox.
result Specialized attention circuits (clustering heads) naturally emerge during training.
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.
The study examines the dynamic behavior of RMSprop and Adam algorithms.
problem Understanding the training loss curve patterns of adaptive gradient algorithms.
method Careful numerical experiments and theoretical explanations using the signGD flow.
result Adam converges smoother and faster when momentum factors are close to each other.
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…
Neurons perform computations, and convey the results of those computations through the statistical structure of their output spike trains. Here we present a practical method, grounded in the information-theoretic analysis of prediction, for inferring a minimal representation of that structure and for characterizing its…
The paper examines how spike strengths and alignments affect overfitting in linear regression models.
problem The impact of spike strengths and alignments on overfitting in linear regression models.
method Characterization of generalization error through exact expressions and analysis of spike strengths, aspect ratio, and target alignment.
result Increasing spike strength can lead to catastrophic overfitting before benign overfitting, especially in well-specified aligned problems.
This paper introduces a new learning rule for probabilistic SNNs that improves log-likelihood, accuracy, and calibration.
problem Training and inference of deterministic SNNs are constrained by their inability to generate multiple independent outputs.
method Introduces a generalized expectation-maximization (GEM) learning rule for probabilistic SNNs.
result The GEM-SNN learning rule leads to significant improvements in log-likelihood, accuracy, and calibration.
SNNs enhance high-frequency price spike forecasting in HFT environments.
problem Conventional financial models fail to capture fine temporal structure in high-frequency price spikes.
method Application of Spiking Neural Networks (SNNs) with hyperparameter tuning via Bayesian Optimization (BO).
result SNN models optimized with PSA achieve significantly higher cumulative returns in backtesting.
The paper reveals low-rank structure in neural network gradients, influenced by data and model parameters.
problem Investigating low-rank structure in gradients of neural networks under relaxed assumptions.
method Spiked data model, relaxation of isotropy assumptions, analysis of mean-field and neural-tangent-kernel scalings.
result Gradient of input weights is approximately low rank, dominated by two rank-one terms.
SNNs can represent complex functions efficiently.
problem Understanding the representational power of SNNs.
method Viewed as sequence-to-sequence processors, analyzed using spike train functions.
result SNNs have the universal representation property for certain functions.
Third-generation neural networks, or Spiking Neural Networks (SNNs), aim at harnessing the energy efficiency of spike-domain processing by building on computing elements that operate on, and exchange, spikes. In this paper, the problem of training a two-layer SNN is studied for the purpose of classification, under a Ge…
Affine spiking neural networks learn efficiently and generalize well.
problem Learning with spiking neural networks, especially with positive weights.
method Affine encoders and decoders, continuous parameter dependence, gradient-based training.
result Affine spiking neural networks can approximate shallow ReLU networks and generalize well.
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…
Extracting and detecting spike activities from the fluorescence observations is an important step in understanding how neuron systems work. The main challenge lies in that the combination of the ambient noise with dynamic baseline fluctuation, often contaminates the observations, thereby deteriorating the reliability o…
New method improves neural spike train models by minimizing divergence directly, leading to better performance.
problem Poor performance and divergence issues in spike train models using maximum likelihood estimation.
method Directly minimize maximum mean discrepancy using spike train kernels and stochastic optimization.
result The proposed method generates well-behaved models with better control over feature trade-offs.
New method detects spike-and-wave epileptiform discharges using Kendall's Tau-b.
problem Detecting spike-and-wave epileptiform discharges in EEG signals.
method Proposes a new method based on Kendall's Tau-b coefficient.
result High Specificity and rule in (SpPIn) for spike-and-wave discharge detection.
Develops generic spike-and-slab priors for high-dimensional linear regression.
problem Bayesian high-dimensional linear regression challenges.
method Proposes a class of generic spike-and-slab priors and a unified framework for theoretical assessment.
result Achieves nearly-optimal posterior contraction rate and model selection consistency under general conditions.
T2FSNN improves deep SNNs by reducing spikes and latency.
problem Inefficiency in spiking neural networks due to lack of scalable training algorithms.
method Introduces time-to-first-spike coding with kernel-based dynamic threshold and dendrite, combined with gradient-based optimization and early firing methods.
result Reduces inference latency and spike count by 22% and less than 1% compared to burst coding.
A central problem of random matrix theory is to understand the eigenvalues of spiked random matrix models, introduced by Johnstone, in which a prominent eigenvector (or "spike") is planted into a random matrix. These distributions form natural statistical models for principal component analysis (PCA) problems throughou…
Improved SNNs with quantized activations outperform traditional networks.
problem Maintaining SotA accuracy in SNNs with limited bit precision.
method Interpolating between non-spiking and spiking regimes using signal processing tools.
result First hybrid SNN outperforms traditional RNNs in accuracy with reduced bit precision.
A learning rule for first-spike times in neural networks reduces energy consumption and reaction times.
problem Energy efficiency and reaction time in neuromorphic systems.
method Derivation of a learning rule for first-spike times in leaky integrate-and-fire neurons, using only input and output spike times.
result Demonstrated that the approach can implement error backpropagation in hierarchical spiking networks and is capable of harnessing neuromorphic system's speed and energy characteristics.
New method uses surrogate gradients to train efficient spiking networks on neuromorphic hardware.
problem Training high-performing spiking networks on analog neuromorphic hardware is challenging due to device mismatch and lack of efficient algorithms.
method Introduces a general in-the-loop learning framework based on surrogate gradients.
result Learning self-corrects for device mismatch, resulting in competitive spiking network performance.
This research bridges binary and spiking neural networks for efficient on-chip AI.
problem Reducing compute requirements in machine learning frameworks.
method Training Spiking Neural Networks in extreme quantization regime and utilizing standard training techniques for conversion.
result Training Spiking Neural Networks in extreme quantization regime achieves near full precision accuracies.
A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in-vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in-silico.…
Study recovers spike order in noisy tensor estimation without SNR assumptions.
problem Estimating multiple signal vectors from noisy tensor observations.
method Gradient flow optimization of a nonconvex function.
result Determines sample complexity for efficient permutation recovery.
This paper analyzes generalization for linear models with spiked covariance structures.
problem Understanding the generalization performance of linear models with spiked covariance structures.
method Derives the generalization error for two simple models with spiked covariances using random matrix theory.
result The eigenvector and eigenvalue corresponding to the spike significantly influence the generalization error.
This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to the…
Algorithm detects and estimates correlated signals in spiked matrices.
problem Detect and estimate correlated signals in spiked matrices.
method Proposes an efficient algorithm based on counting edge-decorated cycles.
result Algorithm succeeds under certain signal-to-noise ratio conditions.
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…
Spiking neural networks perform similarly to deep networks on occluded images.
problem Robust object recognition in partially occluded images.
method Developed a two-layer spiking neural network trained on natural scenes with a biologically plausible learning rule, compared to deep convolutional networks.
result Spiking neural networks achieve good accuracy and robustness on stepwise pixel erasement tasks.
We develop a new theoretical framework, the \emph{envelope complexity}, to analyze the minimax regret with logarithmic loss functions and derive a Bayesian predictor that adaptively achieves the minimax regret over high-dimensional ℓ1-balls within a factor of two. The prior is newly derived for achieving the mini…
Spike-and-slab priors are improved for high-dimensional Bayesian regression.
problem Prohibitive computational costs for existing samplers in high-dimensional settings.
method Proposes Scalable Spike-and-Slab (S3) for high-dimensional Bayesian regression. result Improves computational cost to max{n2pt,np} per iteration, demonstrating significant speed-ups and quality gains. Spiking neural networks (SNNs) have garnered a great amount of interest for supervised and unsupervised learning applications. This paper deals with the problem of training multi-layer feedforward SNNs. The non-linear integrate-and-fire dynamics employed by spiking neurons make it difficult to train SNNs to generate de…
Develops path integral for spiked tensor model dynamics.
problem Dynamics of spiked tensor model with random initial conditions.
method Path integral approach applied to partial differential equations.
result Large-N saddle point equations dominated by melonic diagrams. Method reconstructs neuron models from spike times efficiently.
problem Reconstructing neuron models from spike times in degenerate populations.
method Combining deep learning with DICs to map spike times to DIC densities and generate degenerate CBM populations.
result Fast and scalable reconstruction of degenerate populations from spike recordings.