Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCompressing deep neural networks by matrix product operators
117
0
0.0
(
0
)
Added by
Ze-Feng Gao
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
A deep neural network is a parametrization of a multilayer mapping of signals in terms of many alternatively arranged linear and nonlinear transformations. The linear transformations, which are generally used in the fully connected as well as convolutional layers, contain most of the variational parameters that are trained and stored. Compressing a deep neural network to reduce its number of variational parameters but not its prediction power is an important but challenging problem toward the establishment of an optimized scheme in training efficiently these parameters and in lowering the risk of overfitting. Here we show that this problem can be effectively solved by representing linear transformations with matrix product operators (MPOs), which is a tensor network originally proposed in physics to characterize the short-range entanglement in one-dimensional quantum states. We have tested this approach in five typical neural networks, including FC2, LeNet-5, VGG, ResNet, and DenseNet on two widely used data sets, namely, MNIST and CIFAR-10, and found that this MPO representation indeed sets up a faithful and efficient mapping between input and output signals, which can keep or even improve the prediction accuracy with a dramatically reduced number of parameters. Our method greatly simplifies the representations in deep learning, and opens a possible route toward establishing a framework of modern neural networks which might be simpler and cheaper, but more efficient.
rate research
Read More
Long Short-Term Memory (LSTM) models are the building blocks of many state-of-the-art algorithms for Natural Language Processing (NLP). But, there are a large number of parameters in an LSTM model. This usually brings out a large amount of memory space needed for operating an LSTM model. Thus, an LSTM model usually requires a large amount of computational resources for training and predicting new data, suffering from computational inefficiencies. Here we propose an alternative LSTM model to reduce the number of parameters significantly by representing the weight parameters based on matrix product operators (MPO), which are used to characterize the local correlation in quantum states in physics. We further experimentally compare the compressed models based the MPO-LSTM model and the pruning method on sequence classification and sequence prediction tasks. The experimental results show that our proposed MPO-based method outperforms the pruning method.
Deep neural network (DNN) models have recently obtained state-of-the-art prediction accuracy for the transcription factor binding (TFBS) site classification task. However, it remains unclear how these approaches identify meaningful DNA sequence signals and give insights as to why TFs bind to certain locations. In this paper, we propose a toolkit called the Deep Motif Dashboard (DeMo Dashboard) which provides a suite of visualization strategies to extract motifs, or sequence patterns from deep neural network models for TFBS classification. We demonstrate how to visualize and understand three important DNN models: convolutional, recurrent, and convolutional-recurrent networks. Our first visualization method is finding a test sequences saliency map which uses first-order derivatives to describe the importance of each nucleotide in making the final prediction. Second, considering recurrent models make predictions in a temporal manner (from one end of a TFBS sequence to the other), we introduce temporal output scores, indicating the prediction score of a model over time for a sequential input. Lastly, a class-specific visualization strategy finds the optimal input sequence for a given TFBS positive class via stochastic gradient optimization. Our experimental results indicate that a convolutional-recurrent architecture performs the best among the three architectures. The visualization techniques indicate that CNN-RNN makes predictions by modeling both motifs as well as dependencies among them.
The pervasiveness of Internet-of-Things in our daily life has led to a recent surge in fog computing, encompassing a collaboration of cloud computing and edge intelligence. To that effect, deep learning has been a major driving force towards enabling such intelligent systems. However, growing model sizes in deep learning pose a significant challenge towards deployment in resource-constrained edge devices. Moreover, in a distributed intelligence environment, efficient workload distribution is necessary between edge and cloud systems. To address these challenges, we propose a conditionally deep hybrid neural network for enabling AI-based fog computing. The proposed network can be deployed in a distributed manner, consisting of quantized layers and early exits at the edge and full-precision layers on the cloud. During inference, if an early exit has high confidence in the classification results, it would allow samples to exit at the edge, and the deeper layers on the cloud are activated conditionally, which can lead to improved energy efficiency and inference latency. We perform an extensive design space exploration with the goal of minimizing energy consumption at the edge while achieving state-of-the-art classification accuracies on image classification tasks. We show that with binarized layers at the edge, the proposed conditional hybrid network can process 65% of inferences at the edge, leading to 5.5x computational energy reduction with minimal accuracy degradation on CIFAR-10 dataset. For the more complex dataset CIFAR-100, we observe that the proposed network with 4-bit quantization at the edge achieves 52% early classification at the edge with 4.8x energy reduction. The analysis gives us insights on designing efficient hybrid networks which achieve significantly higher energy efficiency than full-precision networks for edge-cloud based distributed intelligence systems.
We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect the output of the network, and suggest Path-SGD, which is an approximate steepest descent method with respect to a path-wise regularizer related to max-norm regularization. Path-SGD is easy and efficient to implement and leads to empirical gains over SGD and AdaGrad.
Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices. Extensive research work have been conducted on DNN model compression or pruning. However, most of the previous work took heuristic approaches. This work proposes a progressive weight pruning approach based on ADMM (Alternating Direction Method of Multipliers), a powerful technique to deal with non-convex optimization problems with potentially combinatorial constraints. Motivated by dynamic programming, the proposed method reaches extremely high pruning rate by using partial prunings with moderate pruning rates. Therefore, it resolves the accuracy degradation and long convergence time problems when pursuing extremely high pruning ratios. It achieves up to 34 times pruning rate for ImageNet dataset and 167 times pruning rate for MNIST dataset, significantly higher than those reached by the literature work. Under the same number of epochs, the proposed method also achieves faster convergence and higher compression rates. The codes and pruned DNN models are released in the link bit.ly/2zxdlss
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
