Automation has been gradually transforming the workplace for years (think Excel spreadsheets or chatbots). As artificial intelligence (AI), machine learning and deep learning systems that can learn from each other become more prevalent and smarter (think Alexa or IBM Watson), they continue to replace more manual, repetitive job tasks. Consequently, automation and robots are changing more jobs globally at breakneck speed. A McKinsey Global Institute report suggests that between 400 million to 800 million jobs worldwide will be lost due to automation by 2030. The report claims that the U.S. could lose between 16 to 54 million jobs by 2030.

Abstract--Smart Manufacturing refers to optimization techniques that are implemented in production operations by utilizing advanced analytics approaches. With the widespread increase in deploying Industrial Internet of Things (IIoT) sensors in manufacturing processes, there is a progressive need for optimal and effective approaches to data management. Embracing Machine Learning and Artificial Intelligence to take advantage of manufacturing data can lead to efficient and intelligent automation. In this paper, we conduct a comprehensive analysis based on Evolutionary Computing and Deep Learning algorithms toward making semiconductor manufacturing smart. Computing, in manufacturing, provides access to valuable data at different levels, i.e., manufacturing enterprise, manufacturing equipment, and manufacturing processes. VER recent decades, the manufacturing industry witnessed tremendous advances in the form of four major manufacturing insights. Manufacturing, then, can be controlled paradigm shifts. In the latest industrial revolution, Industry 4.0, by leading-edge CI and Artificial Intelligence (AI), and tasks manufacturing has embraced the Industrial Internet of Things are modelled based on experimental observations, to enhance (IIoT) [1]-[3] and Machine Learning (ML) to enable machinery productivity while reducing costs. In doing so, it is of so can make industry processes smart. Broadly speaking, Smart great importance to identify which factors play a pivotal role in Manufacturing (SM) can be defined as a data-driven approach process outcomes.

Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. Currently, most defense methods are designed to defend against additive noise attacks, their performance cannot be guaranteed when against non-additive noise attacks. In this paper, we focus on adversarial deformations, a typical class of non-additive noise attacks, and propose a flow gradient regularization with random start to improve the resistance of models. Theoretically, we prove that, compared with input gradient regularization, regularizing flow gradients is able to get a tighter bound. Across multiple datasets, architectures, and adversarial deformations, our experimental results consistently indicate that models trained with flow gradient regularization can acquire a better resistance than trained with input gradient regularization with a large margin. Moreover, compared with adversarial training, our method can achieve better results in optimization-based and gradient-free attacks, and combining these two methods can improve the resistance against deformation attacks further. Finally, we give a unified form of gradient regularization, which can be used to derive the corresponding form when facing other types of attack.

We propose a novel simulation model that is able to predict the per-level churn and pass rates of Angry Birds Dream Blast, a popular mobile free-to-play game. Our primary contribution is to combine AI gameplay using Deep Reinforcement Learning (DRL) with a simulation of how the player population evolves over the levels. The AI players predict level difficulty, which is used to drive a player population model with simulated skill, persistence, and boredom. This allows us to model, e.g., how less persistent and skilled players are more sensitive to high difficulty, and how such players churn early, which makes the player population and the relation between difficulty and churn evolve level by level. Our work demonstrates that player behavior predictions produced by DRL gameplay can be significantly improved by even a very simple population-level simulation of individual player differences, without requiring costly retraining of agents or collecting new DRL gameplay data for each simulated player.

Due to the automatic feature extraction procedure via multi-layer nonlinear transformations, the deep learning-based visual trackers have recently achieved great success in challenging scenarios for visual tracking purposes. Although many of those trackers utilize the feature maps from pre-trained convolutional neural networks (CNNs), the effects of selecting different models and exploiting various combinations of their feature maps are still not compared completely. To the best of our knowledge, all those methods use a fixed number of convolutional feature maps without considering the scene attributes (e.g., occlusion, deformation, and fast motion) that might occur during tracking. As a pre-requisition, this paper proposes adaptive discriminative correlation filters (DCF) based on the methods that can exploit CNN models with different topologies. First, the paper provides a comprehensive analysis of four commonly used CNN models to determine the best feature maps of each model. Second, with the aid of analysis results as attribute dictionaries, adaptive exploitation of deep features is proposed to improve the accuracy and robustness of visual trackers regarding video characteristics. Third, the generalization of the proposed method is validated on various tracking datasets as well as CNN models with similar architectures. Finally, extensive experimental results demonstrate the effectiveness of the proposed adaptive method compared with state-of-the-art visual tracking methods.

Network pruning can reduce the high computation cost of deep neural network (DNN) models. However, to maintain their accuracies, sparse models often carry randomly-distributed weights, leading to irregular computations. Consequently, sparse models cannot achieve meaningful speedup on commodity hardware (e.g., GPU) built for dense matrix computations. As such, prior works usually modify or design completely new sparsity-optimized architectures for exploiting sparsity. We propose an algorithm-software co-designed pruning method that achieves latency speedups on existing dense architectures. Our work builds upon the insight that the matrix multiplication generally breaks the large matrix into multiple smaller tiles for parallel execution. We propose a tiling-friendly "tile-wise" sparsity pattern, which maintains a regular pattern at the tile level for efficient execution but allows for irregular, arbitrary pruning at the global scale to maintain the high accuracy. We implement and evaluate the sparsity pattern on GPU tensor core, achieving a 1.95x speedup over the dense model.

Recently, learning-based models have enhanced the performance of single-image super-resolution (SISR). However, applying SISR successively to each video frame leads to a lack of temporal coherency. Convolutional neural networks (CNNs) outperform traditional approaches in terms of image quality metrics such as peak signal to noise ratio (PSNR) and structural similarity (SSIM). However, generative adversarial networks (GANs) offer a competitive advantage by being able to mitigate the issue of a lack of finer texture details, usually seen with CNNs when super-resolving at large upscaling factors. We present iSeeBetter, a novel GAN-based spatio-temporal approach to video super-resolution (VSR) that renders temporally consistent super-resolution videos. iSeeBetter extracts spatial and temporal information from the current and neighboring frames using the concept of recurrent back-projection networks as its generator. Furthermore, to improve the "naturality" of the super-resolved image while eliminating artifacts seen with traditional algorithms, we utilize the discriminator from super-resolution generative adversarial network (SRGAN). Although mean squared error (MSE) as a primary loss-minimization objective improves PSNR/SSIM, these metrics may not capture fine details in the image resulting in misrepresentation of perceptual quality. To address this, we use a four-fold (MSE, perceptual, adversarial, and total-variation (TV)) loss function. Our results demonstrate that iSeeBetter offers superior VSR fidelity and surpasses state-of-the-art performance.

Deep learning-based image reconstruction methods have achieved promising results across multiple MRI applications. However, most approaches require large-scale fully-sampled ground truth data for supervised training. Acquiring fully-sampled data is often either difficult or impossible, particularly for dynamic contrast enhancement (DCE), 3D cardiac cine, and 4D flow. We present a deep learning framework for MRI reconstruction without any fully-sampled data using generative adversarial networks. We test the proposed method in two scenarios: retrospectively undersampled fast spin echo knee exams and prospectively undersampled abdominal DCE. The method recovers more anatomical structure compared to conventional methods.

Recently, deep learning approaches for accelerated MRI have been extensively studied thanks to their high performance reconstruction in spite of significantly reduced runtime complexity. These neural networks are usually trained in a supervised manner, so matched pairs of subsampled and fully sampled k-space data are required. Unfortunately, it is often difficult to acquire matched fully sampled k-space data, since the acquisition of fully sampled k-space data requires long scan time and often leads to the change of the acquisition protocol. Therefore, unpaired deep learning without matched label data has become a very important research topic. In this paper, we propose an unpaired deep learning approach using a optimal transport driven cycle-consistent generative adversarial network (OT-cycleGAN) that employs a single pair of generator and discriminator. The proposed OT-cycleGAN architecture is rigorously derived from a dual formulation of the optimal transport formulation using a specially designed penalized least squares cost. The experimental results show that our method can reconstruct high resolution MR images from accelerated k- space data from both single and multiple coil acquisition, without requiring matched reference data.

Deep convolutional neural networks (CNN) have achieved the unwavering confidence in its performance on image processing tasks. The CNN architecture constitutes a variety of different types of layers including the convolution layer and the max-pooling layer. CNN practitioners widely understand the fact that the stability of learning depends on how to initialize the model parameters in each layer. Nowadays, no one doubts that the de facto standard scheme for initialization is the so-called Kaiming initialization that has been developed by He et al. The Kaiming scheme was derived from a much simpler model than the currently used CNN structure having evolved since the emergence of the Kaiming scheme. The Kaiming model consists only of the convolution and fully connected layers, ignoring the max-pooling layer and the global average pooling layer. In this study, we derived the initialization scheme again not from the simplified Kaiming model, but precisely from the modern CNN architectures, and empirically investigated how the new initialization method performs compared to the de facto standard ones that are widely used today.