Compact Neural Representation Using Attentive Network Pruning

• URL: http://arxiv.org/abs/2005.04559v1
• Date: Sun, 10 May 2020 03:20:01 GMT
• Title: Compact Neural Representation Using Attentive Network Pruning
• Authors: Mahdi Biparva, John Tsotsos
• Abstract summary: We describe a Top-Down attention mechanism that is added to a Bottom-Up feedforward network to select important connections and subsequently prune redundant ones at all parametric layers. Our method not only introduces a novel hierarchical selection mechanism as the basis of pruning but also remains competitive with previous baseline methods in the experimental evaluation.
• Score: 1.0152838128195465
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks have evolved to become power demanding and consequently difficult to apply to small-size mobile platforms. Network parameter reduction methods have been introduced to systematically deal with the computational and memory complexity of deep networks. We propose to examine the ability of attentive connection pruning to deal with redundancy reduction in neural networks as a contribution to the reduction of computational demand. In this work, we describe a Top-Down attention mechanism that is added to a Bottom-Up feedforward network to select important connections and subsequently prune redundant ones at all parametric layers. Our method not only introduces a novel hierarchical selection mechanism as the basis of pruning but also remains competitive with previous baseline methods in the experimental evaluation. We conduct experiments using different network architectures on popular benchmark datasets to show high compression ratio is achievable with negligible loss of accuracy.

Related papers

• Opening the Black Box: predicting the trainability of deep neural networks with reconstruction entropy [0.0]
  We present a method for predicting the trainable regime in parameter space for deep feedforward neural networks. For both the MNIST and CIFAR10 datasets, we show that a single epoch of training is sufficient to predict the trainability of the deep feedforward network.
  arXiv  Detail & Related papers  (2024-06-13T18:00:05Z)
• Spike-and-slab shrinkage priors for structurally sparse Bayesian neural networks [0.16385815610837165]
  Sparse deep learning addresses challenges by recovering a sparse representation of the underlying target function. Deep neural architectures compressed via structured sparsity provide low latency inference, higher data throughput, and reduced energy consumption. We propose structurally sparse Bayesian neural networks which prune excessive nodes with (i) Spike-and-Slab Group Lasso (SS-GL), and (ii) Spike-and-Slab Group Horseshoe (SS-GHS) priors.
  arXiv  Detail & Related papers  (2023-08-17T17:14:18Z)
• Rank Diminishing in Deep Neural Networks [71.03777954670323]
  Rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear.
  arXiv  Detail & Related papers  (2022-06-13T12:03:32Z)
• A Dimensionality Reduction Approach for Convolutional Neural Networks [0.0]
  We propose a generic methodology to reduce the number of layers of a pre-trained network by combining the aforementioned techniques for dimensionality reduction with input-output mappings. Our experiment shows that the reduced nets can achieve a level of accuracy similar to the original Convolutional Neural Network under examination, while saving in memory allocation.
  arXiv  Detail & Related papers  (2021-10-18T10:31:12Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• Semi-supervised Network Embedding with Differentiable Deep Quantisation [81.49184987430333]
  We develop d-SNEQ, a differentiable quantisation method for network embedding. d-SNEQ incorporates a rank loss to equip the learned quantisation codes with rich high-order information. It is able to substantially compress the size of trained embeddings, thus reducing storage footprint and accelerating retrieval speed.
  arXiv  Detail & Related papers  (2021-08-20T11:53:05Z)
• Implicit recurrent networks: A novel approach to stationary input processing with recurrent neural networks in deep learning [0.0]
  In this work, we introduce and test a novel implementation of recurrent neural networks into deep learning. We provide an algorithm which implements the backpropagation algorithm on a implicit implementation of recurrent networks. A single-layer implicit recurrent network is able to solve the XOR problem, while a feed-forward network with monotonically increasing activation function fails at this task.
  arXiv  Detail & Related papers  (2020-10-20T18:55:32Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• ESPN: Extremely Sparse Pruned Networks [50.436905934791035]
  We show that a simple iterative mask discovery method can achieve state-of-the-art compression of very deep networks. Our algorithm represents a hybrid approach between single shot network pruning methods and Lottery-Ticket type approaches.
  arXiv  Detail & Related papers  (2020-06-28T23:09:27Z)
• Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks [107.77595511218429]
  In this paper, we investigate the empirical Rademacher complexity related to intermediate layers of deep neural networks. We propose a feature distortion method (Disout) for addressing the aforementioned problem. The superiority of the proposed feature map distortion for producing deep neural network with higher testing performance is analyzed and demonstrated.
  arXiv  Detail & Related papers  (2020-02-23T13:59:13Z)
• Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection [21.48875255723581]
  A mixed-precision quantized neural network with progressively ecreasing bitwidth is proposed to improve the trade-off between accuracy and compression. Experiments on typical network architectures and benchmark datasets demonstrate that the proposed method could achieve better or comparable results.
  arXiv  Detail & Related papers  (2019-12-29T14:11:33Z)

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.