Heterogeneous quantization regularizes spiking neural network activity

• URL: http://arxiv.org/abs/2409.18396v1
• Date: Fri, 27 Sep 2024 02:25:44 GMT
• Title: Heterogeneous quantization regularizes spiking neural network activity
• Authors: Roy Moyal, Kyrus R. Mama, Matthew Einhorn, Ayon Borthakur, Thomas A. Cleland,
• Abstract summary: We present a data-blind neuromorphic signal conditioning strategy whereby analog data are normalized and quantized into spike phase representations. We extend this mechanism by adding a data-aware calibration step whereby the range and density of the quantization weights adapt to accumulated input statistics.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The learning and recognition of object features from unregulated input has been a longstanding challenge for artificial intelligence systems. Brains are adept at learning stable representations given small samples of noisy observations; across sensory modalities, this capacity is aided by a cascade of signal conditioning steps informed by domain knowledge. The olfactory system, in particular, solves a source separation and denoising problem compounded by concentration variability, environmental interference, and unpredictably correlated sensor affinities. To function optimally, its plastic network requires statistically well-behaved input. We present a data-blind neuromorphic signal conditioning strategy whereby analog data are normalized and quantized into spike phase representations. Input is delivered to a column of duplicated spiking principal neurons via heterogeneous synaptic weights; this regularizes layer utilization, yoking total activity to the network's operating range and rendering internal representations robust to uncontrolled open-set stimulus variance. We extend this mechanism by adding a data-aware calibration step whereby the range and density of the quantization weights adapt to accumulated input statistics, optimizing resource utilization by balancing activity regularization and information retention.

Related papers

• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture. We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• Impact of spiking neurons leakages and network recurrences on event-based spatio-temporal pattern recognition [0.0]
  Spiking neural networks coupled with neuromorphic hardware and event-based sensors are getting increased interest for low-latency and low-power inference at the edge. We explore the impact of synaptic and membrane leakages in spiking neurons.
  arXiv  Detail & Related papers  (2022-11-14T21:34:02Z)
• SPIQ: Data-Free Per-Channel Static Input Quantization [37.82255888371488]
  Methods for efficient inference have drawn a growing attention in the machine learning community. In this work, we argue that static input quantization can reach the accuracy levels of dynamic methods by means of a per-channel input quantization scheme. We show through a thorough empirical evaluation on multiple computer vision problems that the proposed method, dubbed SPIQ, achieves accuracies rivalling dynamic approaches with static-level inference speed.
  arXiv  Detail & Related papers  (2022-03-28T10:59:18Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Convolutional generative adversarial imputation networks for spatio-temporal missing data in storm surge simulations [86.5302150777089]
  Generative Adversarial Imputation Nets (GANs) and GAN-based techniques have attracted attention as unsupervised machine learning methods. We name our proposed method as Con Conval Generative Adversarial Imputation Nets (Conv-GAIN)
  arXiv  Detail & Related papers  (2021-11-03T03:50:48Z)
• Deep Metric Learning with Locality Sensitive Angular Loss for Self-Correcting Source Separation of Neural Spiking Signals [77.34726150561087]
  We propose a methodology based on deep metric learning to address the need for automated post-hoc cleaning and robust separation filters. We validate this method with an artificially corrupted label set based on source-separated high-density surface electromyography recordings. This approach enables a neural network to learn to accurately decode neurophysiological time series using any imperfect method of labelling the signal.
  arXiv  Detail & Related papers  (2021-10-13T21:51:56Z)
• Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
  Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
  arXiv  Detail & Related papers  (2021-02-23T20:59:30Z)
• 'Place-cell' emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space [0.0]
  We study the learning dynamics of Restricted Boltzmann Machines (RBM), a neural network paradigm for representation learning. As learning proceeds from a random configuration of the network weights, we show the existence of a symmetry-breaking phenomenon. This symmetry-breaking phenomenon takes place only if the amount of data available for training exceeds some critical value.
  arXiv  Detail & Related papers  (2019-12-30T14:37:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.