Name
Title | ||
|---|---|---|
Deep Adaptive Network: An Efficient Deep Neural Network with Sparse Binary Connections. |
Abstract | ||
|---|---|---|
Deep neural networks are state-of-the-art models for understanding the content of images, video and raw input data. However, implementing a deep neural network in embedded systems is a challenging task, because a typical deep neural network, such as a Deep Belief Network using 128x128 images as input, could exhaust Giga bytes of memory and result in bandwidth and computing bottleneck. To address this challenge, this paper presents a hardware-oriented deep learning algorithm, named as the Deep Adaptive Network, which attempts to exploit the sparsity in the neural connections. The proposed method adaptively reduces the weights associated with negligible features to zero, leading to sparse feedforward network architecture. Furthermore, since the small proportion of important weights are significantly larger than zero, they can be robustly thresholded and represented using single-bit integers (-1 and +1), leading to implementations of deep neural networks with sparse and binary connections. Our experiments showed that, for the application of recognizing MNIST handwritten digits, the features extracted by a two-layer Deep Adaptive Network with about 25% reserved important connections achieved 97.2% classification accuracy, which was almost the same with the standard Deep Belief Network (97.3%). Furthermore, for efficient hardware implementations, the sparse-and-binary-weighted deep neural network could save about 99.3% memory and 99.9% computation units without significant loss of classification accuracy for pattern recognition applications. |
Year | Venue | Field |
|---|---|---|
2016 | arXiv: Learning | Bottleneck,MNIST database,Computer science,Deep belief network,Network architecture,Probabilistic neural network,Time delay neural network,Artificial intelligence,Deep learning,Artificial neural network,Machine learning |
DocType | Volume | Citations |
Journal | abs/1604.06154 | 3 |
PageRank | References | Authors |
0.42 | 17 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xi-chuan Zhou | 1 | 40 | 15.18 |
| Shengli Li | 2 | 184 | 18.06 |
| Kai Qin | 3 | 27 | 7.95 |
| Kunping Li | 4 | 3 | 0.76 |
| Fang Tang | 5 | 38 | 6.41 |
| shengdong hu | 6 | 3 | 1.44 |
| Shujun Liu | 7 | 15 | 6.06 |
| Zhi Lin | 8 | 119 | 12.38 |