Batch Normalization

Peer-to-peer deep learning with non-IID data

In the training process of convolutional neural networks (CNN), a batch normalization (BN) layer is often inserted after a convolution layer to accelerate the convergence of CNN training. In this work, we propose a BN processor that supports both the training and inference processes. To speed up the training of CNN, the proposed work develops an efficient dataflow integrating a novel BN processor design and the processing elements for convolution acceleration. We exploited the similarities in the calculations required for the BN forward and backward passes by sharing hardware elements between both passes, therefore reducing the area overhead. In addition to functional verification of the BN processor, we also completed Automatic Placement & Routing (APR) and conducted post-APR simulation on neural network training. Finally, the proposed solution not only significantly speeds up the CNN training process, but also achieves hardware saving.

Batch Normalization (BatchNorm) is a technique that improves the training of deep neural networks, especially Convolutional Neural Networks (CNN). It has been empirically demonstrated that BatchNorm increases performance, stability, and accuracy, although the reasons for such improvements are unclear. BatchNorm includes a normalization step as well as trainable shift and scale parameters. In this paper, we empirically examine the relative contribution to the success of BatchNorm of the normalization step, as compared to the re-parameterization via shifting and scaling. To conduct our experiments, we implement two new optimizers in PyTorch, namely, a version of BatchNorm that we refer to as AffineLayer, which includes the re-parameterization step without normalization, and a version with just the normalization step, that we call BatchNorm-minus. We compare the performance of our AffineLayer and BatchNorm-minus implementations to standard BatchNorm, and we also compare these to the case where no batch normalization is used. We experiment with four ResNet architectures (ResNet18, ResNet34, ResNet50, and ResNet101) over a standard image dataset and multiple batch sizes. Among other findings, we provide empirical evidence that the success of BatchNorm may derive primarily from improved weight initialization.

Contact-map of a protein sequence dictates the global topology of structural fold. Accurate prediction of the contact-map is thus essential to protein 3D structure prediction, which is particularly useful for the protein sequences that do not have close homology templates in the Protein Data Bank. We developed a new method, ResPRE, to predict residue-level protein contacts using inverse covariance matrix (or precision matrix) of multiple sequence alignments (MSAs) through deep residual convolutional neural network training. The approach was tested on a set of 158 non-homologous proteins collected from the CASP experiments and achieved an average accuracy of 50.6% in the top-L long-range contact prediction with L being the sequence length, which is 11.7% higher than the best of other state-of-the-art approaches ranging from coevolution coupling analysis to deep neural network training. Detailed data analyses show that the major advantage of ResPRE lies at the utilization of precision matrix that helps rule out transitional noises of contact-maps compared with the previously used covariance matrix. Meanwhile, the residual network with parallel shortcut layer connections increases the learning ability of deep neural network training. It was also found that appropriate collection of MSAs can further improve the accuracy of final contact-map predictions. The standalone package and online server of ResPRE are made freely available, which should bring important impact on protein structure and function modeling studies in particular for the distant- and non-homology protein targets. https://zhanglab.ccmb.med.umich.edu/ResPRE and https://github.com/leeyang/ResPRE. Supplementary data are available at Bioinformatics online.

Deep Learning (DL) has become a prominent machine learning technique due to the availability of efficient computational resources in the form of Graphics Processing Units (GPUs), large-scale datasets and a variety of models. The newer generation of GPUs are being designed with special emphasis on optimizing performance for DL applications. Also, the availability of easy-to-use DL frameworks—like PyTorch and TensorFlow— has enhanced productivity of domain experts to work on their custom DL applications from diverse domains. However, existing Deep Neural Network (DNN) training approaches may not fully utilize the newly emerging powerful GPUs like the NVIDIA A100—this is the primary issue that we address in this paper. Our motivating analyses show that the GPU utilization on NVIDIA A100 can be as low as 43% using traditional DNN training approaches for small-to-medium DL models and input data size. This paper proposes AccDP—a data-parallel distributed DNN training approach—to accelerate GPU-based DL applications. AccDP exploits the Message Passing Interface (MPI) communication library coupled with the NVIDIA’s Multi-Process Service (MPS) to increase the amount of work assigned to parallel GPUs resulting in higher utilization of compute resources. We evaluate our proposed design on different small-to-medium DL models and input sizes on the state-of-the-art HPC clusters. By injecting more parallelism into DNN training using our approach, the evaluation shows up to 58% improvement in training performance on a single GPU and up to 62% on 16 GPUs compared to regular DNN training. Furthermore, we conduct an in-depth characterization to determine the impact of several DNN training factors and best practices—including the batch size and the number of data loading workers— to optimally utilize GPU devices. To the best of our knowledge, this is the first work that explores the use of MPS and MPI to maximize the utilization of GPUs in distributed DNN training.

Fashion items are hard to classify since there are a million variations in style, texture, and pattern. Image classification is among the noted strengths of convolutional neural networks. This research introduces an improved CNN architecture for fashion classification, utilizing image augmentation and batch normalization to improve model performance and generalization. To make the model more robust, image augmentation techniques like rotation, width and height shift, zoom, and flips were employed. In addition, a Batch Normalization layer is added in the middle, which can help on stabilizing the learning process and accelerating convergence. The proposed model was trained on an augmented dataset, achieving a satisfactory improvement in test accuracy of 91.97% compared to a baseline CNN model, which obtained 88.5% accuracy. According to the results, the image augmentation with the application of Batch Normalization improves the CNN architecture for better effectiveness in fashion classification tasks.

Generalizable person re-identification aims to learn a model with only several labeled source domains that can perform well on unseen domains. Without access to the unseen domain, the feature statistics of the batch normalization (BN) layer learned from a limited number of source domains is doubtlessly biased for unseen domain. This would mislead the feature representation learning for unseen domain and deteriorate the generalizaiton ability of the model. In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization. Specifically, we establish a lightweight model with multiple set of domain-specific BN layers to capture the discriminability of individual source domain, and learn the corresponding parameters of the domain-specific BN layers. These parameters of different source domains are employed to deduce a Gaussian process. We randomly sample several paths from this Gaussian process served as the BN estimations of potential new domains outside of existing source domains, which can further optimize these learned parameters from source domains, and estimate more accurate Gaussian process by them in return, tending to real data distribution. Even without a large number of source domains, GDNorm can still provide debiased BN estimation by using the mean path of the Gaussian process, while maintaining low computational cost during testing. Extensive experiments demonstrate that our GDNorm effectively improves the generalization ability of the model on unseen domain.

In this work, we design a neural network named MCRNN for classifying signals with slight distinction. This model combines advantages of both Convolutional Neural Network and Recurrent Neural Network, allowing the network to distinguish between long signals with long time-frequency maps. We use an architecture involving both convolutional layers, for extracting high-level features and reduce the dimension of data from time-frequency maps, and recurrent layers, for aggregating long-term dependencies. We apply techniques like Adam optimizer, batch normalization, and softmax layers, obtaining highly competitive results of 99.9% accuracy even in a low SNR of -2dB. Moreover, we conduct extensive experiment through a range of noisy scenarios from -10dB to 30dB. The model can be extended to signal dataset with short time-frequency maps easily. We leverage open source dataset like DeepSig as verification.

Traffic sign recognition (TSR) is an important component of automated driving system. It is a rather challenging task to design a high-performance classifier for the TSR system. In this paper, we proposed a new method for TSR system based on deep convolutional neural network. In order to enhance the expression of the network, a novel structure (dubbed block-layer below) which combines Network-in-Network and residual connection was designed. Our network has 10 layers with parameters (block-layer be seen as a single layer); the first seven are alternate convolutional layers and block-layers, and the remaining three are fully-connected layers. We trained our TSR network on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. To reduce overfitting, we did data augmentation on the training images and employed a regularization method named dropout. We also employed a mechanism called Batch Normalization which has been proved to be efficient for accelerating the training of deep neural networks. To speed up the training, we used an efficient GPU to accelerate the convolutional operation. On the test dataset of GTSRB, we achieve the accuracy rate of 98.96%, exceeding the human average raters.

Recently deep-learning (DL) techniques have been widely adopted in side-channel power analysis. A DL-assisted SCA generally consists of two phases: a deep neural network (DNN) training phase and a follow-on attack phase using the trained DNN. However, currently the two phases are not well aligned, as there is no conclusion on what metric used in the training can result in the most effective attack in the second phase. When traditional loss functions such as negative log-likelihood (NLL) are used in training a DNN, the trained model does not yield optimal follow-on attack. Recently some information theoretical SCA leakage metrics are proposed, either as the validation metric to stop the DNN training with traditional loss functions, or as both the validation metric and the training loss function. None of those proposed metrics, however, directly measures the SCA effectiveness. We propose to conduct DNN training directly with a common SCA effectiveness metric, Guessing Entropy (GE). We overcome the prior practical difficulty of using GE in DNN training by utilizing the GEEA estimation algorithm introduced in CHES 2020. We show that using GEEA as either the validation metric or the loss function produces DNN models that lead to much more effective follow-on attacks. Our work consolidates the DL-assisted SCA framework with a consistent metric, which shows great potential to be adopted as the universal SCA-oriented DNN training framework.

The increasing interest in filter pruning of convolutional neural networks stems from its inherent ability to effectively compress and accelerate these networks. Currently, filter pruning is mainly divided into two schools: norm-based and relation-based. These methods aim to selectively remove the least important filters according to predefined rules. However, the limitations of these methods lie in the inadequate consideration of filter diversity and the impact of batch normalization (BN) layers on the input of the next layer, which may lead to performance degradation. To address the above limitations of norm-based and similarity-based methods, this study conducts empirical analyses to reveal their drawbacks and subsequently introduces a groundbreaking complex hybrid weighted pruning method. By evaluating the correlations and norms between individual filters, as well as the parameters of the BN layer, our method effectively identifies and prunes the most redundant filters in a robust manner, thereby avoiding significant decreases in network performance. We conducted comprehensive and direct pruning experiments on different depths of ResNet using publicly available image classification datasets, ImageNet and CIFAR-10. The results demonstrate the significant efficacy of our approach. In particular, when applied to the ResNet-50 on the ImageNet dataset, achieves a significant reduction of 53.5% in floating-point operations, with a performance loss of only 0.6%.

Communication is not always direct; it often involves nuanced elements like humor, irony, and sarcasm. This study introduces a novel two-level approach for sarcasm detection, leveraging Convolutional Neural Networks (CNNs). Convolutional neural networks (CNNs) are crucial for many deep learning applications, yet their deployment on IoT devices is challenged by resource constraints and the need for low latency, particularly in on-device training. Traditional methods of deploying large CNN models on these devices often lead to suboptimal performance and increased energy consumption. To address this, our paper proposes an energy- efficient CNN design by optimising batch normalisation operations. Batch normalisation is vital for deep learning, aiding in faster convergence and stabilising gradient flow, but there has been limited research on creating energy-efficient and lightweight CNNs with optimised batch normalisation. This study proposes a 3R (reduce, reuse, recycle) optimisation technique for batch normalization. This technique introduces an energy-efficient CNN architecture. We investigate the use of batch normalization optimization to streamline memory usage and computational complexity, aiming to uphold or improve model performance on CPU- based systems. Additionally, we evaluate its effectiveness across diverse datasets, focusing on energy efficiency and adaptability in different settings. Furthermore, we analyze how batch normalization influences the performance and effectiveness of activation functions and pooling layers in neural network designs. Our results highlight batch normalization’s ability to enhance computational efficiency, particularly on devices with limited resources.

A bearing fault diagnosis method based on an improved convolutional neural network(CNN) is proposed to address the problem of low accuracy of traditional convolutional neural network for rolling bearing fault identification. First, the convolutional kernels of the first convolutional layer of the original network are widened to accommodate the bearing fault signal with one-dimensional input. Then, the number of convolutional kernels is reduced while maintaining the feature extraction capability of the network to ensure the deepening of the network while strongly suppressing the overfitting phenomenon of the network. Finally, the batch normalization(BN) layer is added after the convolutional and fully connected layers of the convolutional neural network to accelerate the convergence of the network and prevent the network from gradient disappearance or gradient explosion. Experimental results demonstrate that the proposed method achieves higher diagnostic accuracy and stability than traditional convolutional neural network.

Batch Normalization (BN) techniques have been proposed to reduce the so-called Internal Covariate Shift (ICS) by attempting to keep the distributions of layer outputs unchanged. Experiments have shown their effectiveness on training deep neural networks. However, since only the first two moments are controlled in these BN techniques, it seems that a weak constraint is imposed on layer distributions and furthermore whether such constraint can reduce ICS is unknown. Thus this paper proposes a measure for ICS by using the Earth Mover (EM) distance and then derives the upper and lower bounds for the measure to provide a theoretical analysis of BN. The upper bound has shown that BN techniques can control ICS only for the outputs with low dimensions and small noise whereas their control is not effective in other cases. This paper also proves that such control is just a bounding of ICS rather than a reduction of ICS. Meanwhile, the analysis shows that the high-order moments and noise, which BN cannot control, have great impact on the lower bound. Based on such analysis, this paper furthermore proposes an algorithm that unitizes the outputs with an adjustable parameter to further bound ICS in order to cope with the problems of BN. The upper bound for the proposed unitization is noise-free and only dominated by the parameter. Thus, the parameter can be trained to tune the bound and further to control ICS. Besides, the unitization is embedded into the framework of BN to reduce the information loss. The experiments show that this proposed algorithm outperforms existing BN techniques on CIFAR-10, CIFAR-100 and ImageNet datasets.

An improved image texture synthesis based on algorithm convolution neural network