Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEfficient batchwise dropout training using submatrices
112
0
0.0
(
0
)
Added by
Benjamin Graham
Publication date
2015
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Dropout is a popular technique for regularizing artificial neural networks. Dropout networks are generally trained by minibatch gradient descent with a dropout mask turning off some of the units---a different pattern of dropout is applied to every sample in the minibatch. We explore a very simple alternative to the dropout mask. Instead of masking dropped out units by setting them to zero, we perform matrix multiplication using a submatrix of the weight matrix---unneeded hidden units are never calculated. Performing dropout batchwise, so that one pattern of dropout is used for each sample in a minibatch, we can substantially reduce training times. Batchwise dropout can be used with fully-connected and convolutional neural networks.
rate research
Read More
Compared to Multilayer Neural Networks with real weights, Binary Multilayer Neural Networks (BMNNs) can be implemented more efficiently on dedicated hardware. BMNNs have been demonstrated to be effective on binary classification tasks with Expectation BackPropagation (EBP) algorithm on high dimensional text datasets. In this paper, we investigate the capability of BMNNs using the EBP algorithm on multiclass image classification tasks. The performances of binary neural networks with multiple hidden layers and different numbers of hidden units are examined on MNIST. We also explore the effectiveness of image spatial filters and the dropout technique in BMNNs. Experimental results on MNIST dataset show that EBP can obtain 2.12% test error with binary weights and 1.66% test error with real weights, which is comparable to the results of standard BackPropagation algorithm on fully connected MNNs.
Computation using brain-inspired spiking neural networks (SNNs) with neuromorphic hardware may offer orders of magnitude higher energy efficiency compared to the current analog neural networks (ANNs). Unfortunately, training SNNs with the same number of layers as state of the art ANNs remains a challenge. To our knowledge the only method which is successful in this regard is supervised training of ANN and then converting it to SNN. In this work we directly train deep SNNs using backpropagation with surrogate gradient and find that due to implicitly recurrent nature of feed forward SNNs the exploding or vanishing gradient problem severely hinders their training. We show that this problem can be solved by tuning the surrogate gradient function. We also propose using batch normalization from ANN literature on input currents of SNN neurons. Using these improvements we show that is is possible to train SNN with ResNet50 architecture on CIFAR100 and Imagenette object recognition datasets. The trained SNN falls behind in accuracy compared to analogous ANN but requires several orders of magnitude less inference time steps (as low as 10) to reach good accuracy compared to SNNs obtained by conversion from ANN which require on the order of 1000 time steps.
Deep spiking neural networks (SNNs) hold great potential for improving the latency and energy efficiency of deep neural networks through event-based computation. However, training such networks is difficult due to the non-differentiable nature of asynchronous spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are only considered as noise. This enables an error backpropagation mechanism for deep SNNs, which works directly on spike signals and membrane potentials. Thus, compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statics of spikes more precisely. Our novel framework outperforms all previously reported results for SNNs on the permutation invariant MNIST benchmark, as well as the N-MNIST benchmark recorded with event-based vision sensors.
Recurrent Neural Networks (RNNs), more specifically their Long Short-Term Memory (LSTM) variants, have been widely used as a deep learning tool for tackling sequence-based learning tasks in text and speech. Training of such LSTM applications is computationally intensive due to the recurrent nature of hidden state computation that repeats for each time step. While sparsity in Deep Neural Nets has been widely seen as an opportunity for reducing computation time in both training and inference phases, the usage of non-ReLU activation in LSTM RNNs renders the opportunities for such dynamic sparsity associated with neuron activation and gradient values to be limited or non-existent. In this work, we identify dropout induced sparsity for LSTMs as a suitable mode of computation reduction. Dropout is a widely used regularization mechanism, which randomly drops computed neuron values during each iteration of training. We propose to structure dropout patterns, by dropping out the same set of physical neurons within a batch, resulting in column (row) level hidden state sparsity, which are well amenable to computation reduction at run-time in general-purpose SIMD hardware as well as systolic arrays. We conduct our experiments for three representative NLP tasks: language modelling on the PTB dataset, OpenNMT based machine translation using the IWSLT De-En and En-Vi datasets, and named entity recognition sequence labelling using the CoNLL-2003 shared task. We demonstrate that our proposed approach can be used to translate dropout-based computation reduction into reduced training time, with improvement ranging from 1.23x to 1.64x, without sacrificing the target metric.
The state-of-the-art (SOTA) for mixed precision training is dominated by variants of low precision floating point operations, and in particular, FP16 accumulating into FP32 Micikevicius et al. (2017). On the other hand, while a lot of research has also happened in the domain of low and mixed-precision Integer training, these works either present results for non-SOTA networks (for instance only AlexNet for ImageNet-1K), or relatively small datasets (like CIFAR-10). In this work, we train state-of-the-art visual understanding neural networks on the ImageNet-1K dataset, with Integer operations on General Purpose (GP) hardware. In particular, we focus on Integer Fused-Multiply-and-Accumulate (FMA) operations which take two pairs of INT16 operands and accumulate results into an INT32 output.We propose a shared exponent representation of tensors and develop a Dynamic Fixed Point (DFP) scheme suitable for common neural network operations. The nuances of developing an efficient integer convolution kernel is examined, including methods to handle overflow of the INT32 accumulator. We implement CNN training for ResNet-50, GoogLeNet-v1, VGG-16 and AlexNet; and these networks achieve or exceed SOTA accuracy within the same number of iterations as their FP32 counterparts without any change in hyper-parameters and with a 1.8X improvement in end-to-end training throughput. To the best of our knowledge these results represent the first INT16 training results on GP hardware for ImageNet-1K dataset using SOTA CNNs and achieve highest reported accuracy using half-precision
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
