Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBlock-term Tensor Neural Networks
68
0
0.0
(
0
)
Added by
Haiqin Yang
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e.g., image classification, natural language processing, etc. Despite the good performance, the huge number of parameters in DNNs brings challenges to efficient training of DNNs and also their deployment in low-end devices with limited computing resources. In this paper, we explore the correlations in the weight matrices, and approximate the weight matrices with the low-rank block-term tensors. We name the new corresponding structure as block-term tensor layers (BT-layers), which can be easily adapted to neural network models, such as CNNs and RNNs. In particular, the inputs and the outputs in BT-layers are reshaped into low-dimensional high-order tensors with a similar or improved representation power. Sufficient experiments have demonstrated that BT-layers in CNNs and RNNs can achieve a very large compression ratio on the number of parameters while preserving or improving the representation power of the original DNNs.
rate research
Read More
The rapidly growing parameter volume of deep neural networks (DNNs) hinders the artificial intelligence applications on resource constrained devices, such as mobile and wearable devices. Neural network pruning, as one of the mainstream model compression techniques, is under extensive study to reduce the number of parameters and computations. In contrast to irregular pruning that incurs high index storage and decoding overhead, structured pruning techniques have been proposed as the promising solutions. However, prior studies on structured pruning tackle the problem mainly from the perspective of facilitating hardware implementation, without analyzing the characteristics of sparse neural networks. The neglect on the study of sparse neural networks causes inefficient trade-off between regularity and pruning ratio. Consequently, the potential of structurally pruning neural networks is not sufficiently mined. In this work, we examine the structural characteristics of the irregularly pruned weight matrices, such as the diverse redundancy of different rows, the sensitivity of different rows to pruning, and the positional characteristics of retained weights. By leveraging the gained insights as a guidance, we first propose the novel block-max weight masking (BMWM) method, which can effectively retain the salient weights while imposing high regularity to the weight matrix. As a further optimization, we propose a density-adaptive regular-block (DARB) pruning that outperforms prior structured pruning work with high pruning ratio and decoding efficiency. Our experimental results show that DARB can achieve 13$times$ to 25$times$ pruning ratio, which are 2.8$times$ to 4.3$times$ improvements than the state-of-the-art counterparts on multiple neural network models and tasks. Moreover, DARB can achieve 14.3$times$ decoding efficiency than block pruning with higher pruning ratio.
This study compares the modularity performance of two artificial neural network architectures: a Long Short-Term Memory (LSTM) recurrent network, and Morphognosis, a neural network based on a hierarchy of spatial and temporal contexts. Mazes are used to measure performance, defined as the ability to utilize independently learned mazes to solve mazes composed of them. A maze is a sequence of rooms connected by doors. The modular task is implemented as follows: at the beginning of the maze, an initial door choice forms a context that must be retained until the end of an intervening maze, where the same door must be chosen again to reach the goal. For testing, the door-association mazes and separately trained intervening mazes are presented together for the first time. While both neural networks perform well during training, the testing performance of Morphognosis is significantly better than LSTM on this modular task.
Recurrent Neural Networks (RNNs) are used in state-of-the-art models in domains such as speech recognition, machine translation, and language modelling. Sparsity is a technique to reduce compute and memory requirements of deep learning models. Sparse RNNs are easier to deploy on devices and high-end server processors. Even though sparse operations need less compute and memory relative to their dense counterparts, the speed-up observed by using sparse operations is less than expected on different hardware platforms. In order to address this issue, we investigate two different approaches to induce block sparsity in RNNs: pruning blocks of weights in a layer and using group lasso regularization to create blocks of weights with zeros. Using these techniques, we demonstrate that we can create block-sparse RNNs with sparsity ranging from 80% to 90% with small loss in accuracy. This allows us to reduce the model size by roughly 10x. Additionally, we can prune a larger dense network to recover this loss in accuracy while maintaining high block sparsity and reducing the overall parameter count. Our technique works with a variety of block sizes up to 32x32. Block-sparse RNNs eliminate overheads related to data storage and irregular memory accesses while increasing hardware efficiency compared to unstructured sparsity.
We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time and when computing the parameters gradient at train-time. We conduct two sets of experiments, each based on a different framework, namely Torch7 and Theano, where we train BNNs on MNIST, CIFAR-10 and SVHN, and achieve nearly state-of-the-art results. During the forward pass, BNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations, which might lead to a great increase in power-efficiency. Last but not least, we wrote a binary matrix multiplication GPU kernel with which it is possible to run our MNIST BNN 7 times faster than with an unoptimized GPU kernel, without suffering any loss in classification accuracy. The code for training and running our BNNs is available.
Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required by commonly used fully-connected layers, making it hard to use the models on low-end devices and stopping the further increase of the model size. In this paper we convert the dense weight matrices of the fully-connected layers to the Tensor Train format such that the number of parameters is reduced by a huge factor and at the same time the expressive power of the layer is preserved. In particular, for the Very Deep VGG networks we report the compression factor of the dense weight matrix of a fully-connected layer up to 200000 times leading to the compression factor of the whole network up to 7 times.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
