Explore the Knowledge contained in Network Weights to Obtain Sparse Neural Networks

• URL: http://arxiv.org/abs/2103.15590v1
• Date: Fri, 26 Mar 2021 11:29:40 GMT
• Title: Explore the Knowledge contained in Network Weights to Obtain Sparse Neural Networks
• Authors: Mengqiao Han, Xiabi Liu
• Abstract summary: This paper proposes a novel learning approach to obtain sparse fully connected layers in neural networks (NNs) automatically. We design a switcher neural network (SNN) to optimize the structure of the task neural network (TNN)
• Score: 2.649890751459017
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sparse neural networks are important for achieving better generalization and enhancing computation efficiency. This paper proposes a novel learning approach to obtain sparse fully connected layers in neural networks (NNs) automatically. We design a switcher neural network (SNN) to optimize the structure of the task neural network (TNN). The SNN takes the weights of the TNN as the inputs and its outputs are used to switch the connections of TNN. In this way, the knowledge contained in the weights of TNN is explored to determine the importance of each connection and the structure of TNN consequently. The SNN and TNN are learned alternately with stochastic gradient descent (SGD) optimization, targeting at a common objective. After learning, we achieve the optimal structure and the optimal parameters of the TNN simultaneously. In order to evaluate the proposed approach, we conduct image classification experiments on various network structures and datasets. The network structures include LeNet, ResNet18, ResNet34, VggNet16 and MobileNet. The datasets include MNIST, CIFAR10 and CIFAR100. The experimental results show that our approach can stably lead to sparse and well-performing fully connected layers in NNs.

Related papers

• LC-TTFS: Towards Lossless Network Conversion for Spiking Neural Networks with TTFS Coding [55.64533786293656]
  We show that our algorithm can achieve a near-perfect mapping between the activation values of an ANN and the spike times of an SNN on a number of challenging AI tasks. The study paves the way for deploying ultra-low-power TTFS-based SNNs on power-constrained edge computing platforms.
  arXiv  Detail & Related papers  (2023-10-23T14:26:16Z)
• High-performance deep spiking neural networks with 0.3 spikes per neuron [9.01407445068455]
  It is hard to train biologically-inspired spiking neural networks (SNNs) than artificial neural networks (ANNs) We show that training deep SNN models achieves the exact same performance as that of ANNs. Our SNN accomplishes high-performance classification with less than 0.3 spikes per neuron, lending itself for an energy-efficient implementation.
  arXiv  Detail & Related papers  (2023-06-14T21:01:35Z)
• A Hybrid Neural Coding Approach for Pattern Recognition with Spiking Neural Networks [53.31941519245432]
  Brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks. These SNNs are grounded on homogeneous neurons that utilize a uniform neural coding for information representation. In this study, we argue that SNN architectures should be holistically designed to incorporate heterogeneous coding schemes.
  arXiv  Detail & Related papers  (2023-05-26T02:52:12Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing [74.31472195046099]
  We exploit a low-rank tensor-train deep neural network (TT-DNN) to build an end-to-end deep learning pipeline, namely LR-TT-DNN. A hybrid model combining LR-TT-DNN with a convolutional neural network (CNN) is set up to boost the performance. Our empirical evidence demonstrates that the LR-TT-DNN and CNN+(LR-TT-DNN) models with fewer model parameters can outperform the TT-DNN and CNN+(LR-TT-DNN) counterparts.
  arXiv  Detail & Related papers  (2022-03-11T15:55:34Z)
• Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks [72.81092567651395]
  Sub-bit Neural Networks (SNNs) are a new type of binary quantization design tailored to compress and accelerate BNNs. SNNs are trained with a kernel-aware optimization framework, which exploits binary quantization in the fine-grained convolutional kernel space. Experiments on visual recognition benchmarks and the hardware deployment on FPGA validate the great potentials of SNNs.
  arXiv  Detail & Related papers  (2021-10-18T11:30:29Z)
• Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation [5.800785186389827]
  Spiking Neural Networks (SNNs) have emerged as the low-power alternative to Artificial Neural Networks (ANNs) In this paper, we explore the SNN applications beyond classification and present semantic segmentation networks configured with spiking neurons.
  arXiv  Detail & Related papers  (2021-10-14T21:53:03Z)
• Mining the Weights Knowledge for Optimizing Neural Network Structures [1.995792341399967]
  We introduce a switcher neural network (SNN) that uses as inputs the weights of a task-specific neural network (called TNN for short) By mining the knowledge contained in the weights, the SNN outputs scaling factors for turning off neurons in the TNN. In terms of accuracy, we outperform baseline networks and other structure learning methods stably and significantly.
  arXiv  Detail & Related papers  (2021-10-11T05:20:56Z)
• Pruning of Deep Spiking Neural Networks through Gradient Rewiring [41.64961999525415]
  Spiking Neural Networks (SNNs) have been attached great importance due to their biological plausibility and high energy-efficiency on neuromorphic chips. Most existing methods directly apply pruning approaches in artificial neural networks (ANNs) to SNNs, which ignore the difference between ANNs and SNNs. We propose gradient rewiring (Grad R), a joint learning algorithm of connectivity and weight for SNNs, that enables us to seamlessly optimize network structure without retrain.
  arXiv  Detail & Related papers  (2021-05-11T10:05:53Z)
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks [80.15411508088522]
  Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency. We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
  arXiv  Detail & Related papers  (2020-07-02T15:38:44Z)
• SiamSNN: Siamese Spiking Neural Networks for Energy-Efficient Object Tracking [20.595208488431766]
  SiamSNN is the first deep SNN tracker that achieves short latency and low precision loss on the visual object tracking benchmarks OTB2013, VOT2016, and GOT-10k. SiamSNN notably achieves low energy consumption and real-time on Neuromorphic chip TrueNorth.
  arXiv  Detail & Related papers  (2020-03-17T08:49:51Z)

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.