Dynamic Hard Pruning of Neural Networks at the Edge of the Internet

• URL: http://arxiv.org/abs/2011.08545v3
• Date: Fri, 22 Oct 2021 16:25:58 GMT
• Title: Dynamic Hard Pruning of Neural Networks at the Edge of the Internet
• Authors: Lorenzo Valerio, Franco Maria Nardini, Andrea Passarella and Raffaele Perego
• Abstract summary: Dynamic Hard Pruning (DynHP) technique incrementally prunes the network during training. DynHP enables a tunable size reduction of the final neural network and reduces the NN memory occupancy during training. Freed memory is reused by a emphdynamic batch sizing approach to counterbalance the accuracy degradation caused by the hard pruning strategy.
• Score: 11.605253906375424
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural Networks (NN), although successfully applied to several Artificial Intelligence tasks, are often unnecessarily over-parametrised. In edge/fog computing, this might make their training prohibitive on resource-constrained devices, contrasting with the current trend of decentralising intelligence from remote data centres to local constrained devices. Therefore, we investigate the problem of training effective NN models on constrained devices having a fixed, potentially small, memory budget. We target techniques that are both resource-efficient and performance effective while enabling significant network compression. Our Dynamic Hard Pruning (DynHP) technique incrementally prunes the network during training, identifying neurons that marginally contribute to the model accuracy. DynHP enables a tunable size reduction of the final neural network and reduces the NN memory occupancy during training. Freed memory is reused by a \emph{dynamic batch sizing} approach to counterbalance the accuracy degradation caused by the hard pruning strategy, improving its convergence and effectiveness. We assess the performance of DynHP through reproducible experiments on three public datasets, comparing them against reference competitors. Results show that DynHP compresses a NN up to $10$ times without significant performance drops (up to $3.5\%$ additional error w.r.t. the competitors), reducing up to $80\%$ the training memory occupancy.

Related papers

• SynA-ResNet: Spike-driven ResNet Achieved through OR Residual Connection [10.702093960098104]
  Spiking Neural Networks (SNNs) have garnered substantial attention in brain-like computing for their biological fidelity and the capacity to execute energy-efficient spike-driven operations. We propose a novel training paradigm that first accumulates a large amount of redundant information through OR Residual Connection (ORRC) We then filters out the redundant information using the Synergistic Attention (SynA) module, which promotes feature extraction in the backbone while suppressing the influence of noise and useless features in the shortcuts.
  arXiv  Detail & Related papers  (2023-11-11T13:36:27Z)
• SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks [56.35403810762512]
  Spiking neural networks (SNNs) with event-based computation are promising brain-inspired models for energy-efficient applications on neuromorphic hardware. We study spike-based implicit differentiation on the equilibrium state (SPIDE) that extends the recently proposed training method.
  arXiv  Detail & Related papers  (2023-02-01T04:22:59Z)
• Adversarial training with informed data selection [53.19381941131439]
  Adrial training is the most efficient solution to defend the network against these malicious attacks. This work proposes a data selection strategy to be applied in the mini-batch training. The simulation results show that a good compromise can be obtained regarding robustness and standard accuracy.
  arXiv  Detail & Related papers  (2023-01-07T12:09:50Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Online Training Through Time for Spiking Neural Networks [66.7744060103562]
  Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. We propose online training through time (OTTT) for SNNs, which is derived from BPTT to enable forward-in-time learning.
  arXiv  Detail & Related papers  (2022-10-09T07:47:56Z)
• Inverse-Dirichlet Weighting Enables Reliable Training of Physics Informed Neural Networks [2.580765958706854]
  We describe and remedy a failure mode that may arise from multi-scale dynamics with scale imbalances during training of deep neural networks. PINNs are popular machine-learning templates that allow for seamless integration of physical equation models with data. For inverse modeling using sequential training, we find that inverse-Dirichlet weighting protects a PINN against catastrophic forgetting.
  arXiv  Detail & Related papers  (2021-07-02T10:01:37Z)
• Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update [49.948082497688404]
  Training large-scale deep neural networks (DNNs) currently requires a significant amount of energy, leading to serious environmental impacts. One promising approach to reduce the energy costs is representing DNNs with low-precision numbers. We jointly design a lowprecision training framework involving a logarithmic number system (LNS) and a multiplicative weight update training method, termed LNS-Madam.
  arXiv  Detail & Related papers  (2021-06-26T00:32:17Z)
• SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments [14.727296040550392]
  Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual learning capabilities because of their biological plausibility. We propose SpikeDyn, a framework for energy-efficient SNNs with continual and unsupervised learning capabilities in dynamic environments.
  arXiv  Detail & Related papers  (2021-02-28T08:26:23Z)
• FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training [81.85361544720885]
  We propose FracTrain that integrates progressive fractional quantization which gradually increases the precision of activations, weights, and gradients. FracTrain reduces computational cost and hardware-quantified energy/latency of DNN training while achieving a comparable or better (-0.12%+1.87%) accuracy.
  arXiv  Detail & Related papers  (2020-12-24T05:24:10Z)
• FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks [14.916996986290902]
  Spiking Neural Networks (SNNs) offer unsupervised learning capability due to the spike-timing-dependent plasticity (STDP) rule. However, state-of-the-art SNNs require a large memory footprint to achieve high accuracy. We propose FSpiNN, an optimization framework for obtaining memory- and energy-efficient SNNs for training and inference processing.
  arXiv  Detail & Related papers  (2020-07-17T09:40:26Z)
• A Spike in Performance: Training Hybrid-Spiking Neural Networks with Quantized Activation Functions [6.574517227976925]
  Spiking Neural Network (SNN) is a promising approach to energy-efficient computing. We show how to maintain state-of-the-art accuracy when converting a non-spiking network into an SNN.
  arXiv  Detail & Related papers  (2020-02-10T05:24:27Z)

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.