1-4hit |
A new software based in-situ training (SBIST) method to achieve high accuracies is proposed for binarized neural networks inference accelerator chips in which measured offsets in sense amplifiers (activation binarizers) are transformed into biases in the training software. To expedite this individual training, the initial values for the weights are taken from results of a common forming training process which is conducted in advance by using the offset fluctuation distribution averaged over the fabrication line. SPICE simulation inference results for the accelerator predict that the accuracy recovers to higher than 90% even when the amplifier offset is as large as 40mV only after a few epochs of the individual training.
This letter presents an efficient technique to reduce the computational complexity involved in training binary convolutional neural networks (BCNN). The BCNN training shall be conducted focusing on the optimization of the sign of each weight element rather than the exact value itself in convention; in which, the sign of an element is not likely to be flipped anymore after it has been updated to have such a large magnitude to be clipped out. The proposed technique does not update such elements that have been clipped out and eliminates the computations involved in their optimization accordingly. The complexity reduction by the proposed technique is as high as 25.52% in training the BCNN model for the CIFAR-10 classification task, while the accuracy is maintained without severe degradation.
Naohisa NISHIDA Tatsumi OBA Yuji UNAGAMI Jason PAUL CRUZ Naoto YANAI Tadanori TERUYA Nuttapong ATTRAPADUNG Takahiro MATSUDA Goichiro HANAOKA
Machine learning models inherently memorize significant amounts of information, and thus hiding not only prediction processes but also trained models, i.e., model obliviousness, is desirable in the cloud setting. Several works achieved model obliviousness with the MNIST dataset, but datasets that include complicated samples, e.g., CIFAR-10 and CIFAR-100, are also used in actual applications, such as face recognition. Secret sharing-based secure prediction for CIFAR-10 is difficult to achieve. When a deep layer architecture such as CNN is used, the calculation error when performing secret calculation becomes large and the accuracy deteriorates. In addition, if detailed calculations are performed to improve accuracy, a large amount of calculation is required. Therefore, even if the conventional method is applied to CNN as it is, good results as described in the paper cannot be obtained. In this paper, we propose two approaches to solve this problem. Firstly, we propose a new protocol named Batch-normalizedActivation that combines BatchNormalization and Activation. Since BatchNormalization includes real number operations, when performing secret calculation, parameters must be converted into integers, which causes a calculation error and decrease accuracy. By using our protocol, calculation errors can be eliminated, and accuracy degradation can be eliminated. Further, the processing is simplified, and the amount of calculation is reduced. Secondly, we explore a secret computation friendly and high accuracy architecture. Related works use a low-accuracy, simple architecture, but in reality, a high accuracy architecture should be used. Therefore, we also explored a high accuracy architecture for the CIFAR10 dataset. Our proposed protocol can compute prediction of CIFAR-10 within 15.05 seconds with 87.36% accuracy while providing model obliviousness.
This letter presents a novel technique to achieve a fast inference of the binarized convolutional neural networks (BCNN). The proposed technique modifies the structure of the constituent blocks of the BCNN model so that the input elements for the max-pooling operation are binary. In this structure, if any of the input elements is +1, the result of the pooling can be produced immediately; the proposed technique eliminates such computations that are involved to obtain the remaining input elements, so as to reduce the inference time effectively. The proposed technique reduces the inference time by up to 34.11%, while maintaining the classification accuracy.