TiQSA: Workload Minimization in Convolutional Neural Networks Using Tile Quantization and Symmetry Approximation

Abstract

Convolutional Neural Networks (CNNs) in the Internet-of-Things (IoT)-based applications face stringent constraints, like limited memory capacity and energy resources due to many computations in convolution layers. In order to reduce the computational workload in these layers, this paper proposes a hybrid convolution method in conjunction with a Particle of Swarm Convolution Layer Optimization (PSCLO) algorithm. The hybrid convolution is an approximation that exploits the inherent symmetry of filter termed as symmetry approximation and Winograd algorithm structure termed as tile quantization approximation. PSCLO optimizes the balance between workload reduction and accuracy degradation for each convolution layer by selecting fine-tuned thresholds to control each approximation's intensity. The proposed methods have been evaluated on ImageNet, MNIST, Fashion-MNIST, SVHN, and CIFAR-10 datasets. The proposed techniques achieved ∼5.28x multiplicative workload reduction without significant accuracy degradation (<0.1%) for ImageNet on ResNet-18, which is ∼1.08x less multiplicative workload as compared to state-of-the-art Winograd CNN pruning. For LeNet, ∼3.87x and ∼3.93x was the multiplicative workload reduction for MNIST and Fashion-MNIST datasets. The additive workload reduction was ∼2.5x and ∼2.56x for the respective datasets. There is no significant accuracy loss for MNIST and Fashion-MNIST dataset.

Candlestick Patterns Recognition using CNN-LSTM Model to Predict Financial Trading Position in Stock Market

“…CNN is a network model proposed by Lecun et al in 1998 [13]. CNN is one of the deep learning algorithms commonly used to analyze visual images.…”

Fast Convolution based on Winograd Minimum Filtering: Introduction and Development

“…[46] further explored the use of the Winograd algorithm to optimize the convolution kernel with 4-6bit precision. [47] applied quantization on feature map slices, and applied particle swarm optimization technology to find the threshold of quantization. In addition, [10], [48], [49], [50] also applied 8-bit quantization technique on Winograd convolution.…”