Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise the network at the inference time by applying elaborately designed perturbation to input data. Although several defense methods have been proposed to address specific attacks, other attack methods can circumvent these defense mechanisms. Therefore, we propose Purifying Variational Autoencoder (PuVAE), a method to purify adversarial examples. The proposed method eliminates an adversarial perturbation by projecting an adversarial example on the manifold of each class, and determines the closest projection as a purified sample. We experimentally illustrate the robustness of PuVAE against various attack methods without any prior knowledge. In our experiments, the proposed method exhibits performances competitive with state-of-the-art defense methods, and the inference time is approximately 130 times faster than that of Defense-GAN that is the state-of-the art purifier model.

We present, for the first time, a novel deep neural network architecture called \dcn with a dual-path connection between the input image and output class label for mammogram image processing. This architecture is built upon U-Net, which non-linearly maps the input data into a deep latent space. One path of the \dcnn, the locality preserving learner, is devoted to hierarchically extracting and exploiting intrinsic features of the input, while the other path, called the conditional graph learner, focuses on modeling the input-mask correlations. The learned mask is further used to improve classification results, and the two learning paths complement each other. By integrating the two learners our new architecture provides a simple but effective way to jointly learn the segmentation and predict the class label. Benefiting from the powerful expressive capacity of deep neural networks a more discriminative representation can be learned, in which both the semantics and structure are well preserved. Experimental results show that \dcn achieves the best mammography segmentation and classification simultaneously, outperforming recent state-of-the-art models.

Long Short Term Memory Fully Convolutional Neural Networks (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN) have shown to achieve state-of-the-art performance on the task of classifying time series signals on the old University of California-Riverside (UCR) time series repository. However, there has been no study on why LSTM-FCN and ALSTM-FCN perform well. In this paper, we perform a series of ablation tests (3627 experiments) on LSTM-FCN and ALSTM-FCN to provide a better understanding of the model and each of its sub-module. Results from the ablation tests on ALSTM-FCN and LSTM-FCN show that the these blocks perform better when applied in a conjoined manner. Two z-normalizing techniques, z-normalizing each sample independently and z-normalizing the whole dataset, are compared using a Wilcoxson signed-rank test to show a statistical difference in performance. In addition, we provide an understanding of the impact dimension shuffle has on LSTM-FCN by comparing its performance with LSTM-FCN when no dimension shuffle is applied. Finally, we demonstrate the performance of the LSTM-FCN when the LSTM block is replaced by a GRU, basic RNN, and Dense Block.

In 2017, DeepMind's AlphaGoZero demonstrated in a landmark result that it was possible to achieve superhuman performance in the game of Go starting from random play and learning only via reinforcement learning of a neural network using self-play bootstrapping from Monte-Carlo tree search[9]. Moreover, AlphaGoZero used only fairly minimal game-specific tuning. Subsequently, DeepMind's AlphaZero demonstrated that the same methods could also be used to train extremely strong agents in Chess and Shogi. However, the amount of computation required was large, with DeepMind's main reported run taking about 41 TPU-years in total parallelized over 5000 TPUs [8]. The significant cost of reproducing this work has slowed research, putting it out of reach for all but major companies such as Facebook[11], as well as a few online massively distributed computation projects, notably Leela Zero for Go[14], and Leela Chess Zero for Chess[17]. In this paper, we introduce several new techniques, while also reviving some ideas from pre-AlphaZero research in computer Go and newly applying them to the AlphaZero process. Combined with minor domain-specific heuristic optimizations and overall tuning, these ideas greatly improve the efficiency of self-play learning. Still starting only from random play, training on merely about 30 GPUs for a week our bot KataGo reaches just below the strength of Leela Zero as of Leela Zero's 15-block neural net "LZ130", a likely professional or possibly just-superhuman level when run on strong consumer hardware.

Filled with intricate mazes of high-speed conveyor belts carrying yesterday's garbage, high-tech recycling centers use sophisticated sensors to sort plastic from paper from aluminum. While this technology may streamline sorting, it's not smart or nimble enough to finish the job. Behind the scenes, recycling workers continue to sort the materials, making sure cereal boxes don't mix with soda cans. But the future of smart recycling is looking brighter. Spider-like robotic arms, guided by cameras and artificial intelligence (AI) -- think of it as facial-recognition technology for garbage -- are helping to make municipal recycling facilities (MRFs) run more efficiently.

The Human Use of Human Beings, Norbert Wiener's 1950 popularization of his highly influential book Cybernetics: or Control and Communication in the Animal and the Machine (1948), investigates the interplay between human beings and machines in a world in which machines are becoming ever more computationally capable and powerful. It is a remarkably prescient book, and remarkably wrong. Written at the height of the Cold War, it contains a chilling reminder of the dangers of totalitarian organizations and societies, and of the danger to democracy when it tries to combat totalitarianism with totalitarianism's own weapons. Wiener's Cybernetics looked in close scientific detail at the process of control via feedback. Because he was immersed in problems of control, Wiener saw the world as a set of complex, interlocking feedback loops, in which sensors, signals, and actuators such as engines interact via an intricate exchange of signals and information. The engineering applications of Cybernetics were tremendously influential and effective, giving rise to rockets, robots, automated assembly lines, and a host of precision-engineering techniques--in other words, to the basis of contemporary industrial society.

This is about time-series prediction/classification with neural networks using Keras. I will not go into theory or description of recurrent neural nets or LSTM itself, rather there are plenty tutorials out there. Search engines give plenty more. Try some if not already familiar. I just try to focus on what I found confusing after reading those, and how did that go.

Learn how HPE, NVIDIA, WekaIO, and Mellanox have designed a deep learning architecture that accelerates AI insights. Deep learning (DL) architectures offer organizations a way to accelerate AI insights, enabling them to process hundreds of millions of data points and generate AI-based analytics--without slowing down their systems. At HPE, we're offering our technology and expertise to data scientists, solution builders, and IT personnel who recognize the need to successfully implement AI projects. We understand the unique needs of organizations that might hesitate to build the complex IT infrastructure needed to deliver AI insights--which is why we've designed solutions that make it easy for them. To build a storage solution that could accelerate AI training and inferencing, we've collaborated with our partners to develop a scalable, shared storage solution that runs on a neural network.

With the world of artificial intelligence (AI) developing so rapidly, it's not surprising that many people are unclear about the difference between the various kinds of data analysis and how they can drive business. The distinction between machine learning (ML) and deep learning (DL), for example, can be a bit confusing to the uninitiated, but it makes all the difference for companies trying to harness the reams of data they collect, notes this opinion piece by Adam Singolda, CEO and founder of Taboola. Q: How do you do what you do? Hardly a day goes by without news of another company's latest foray into artificial intelligence. While the value of AI may be self-evident in consumer technology products like Cortana or Spotify, can it really benefit everything from toothbrushes to burger joints or rap lyric generation? And is it so easy to do that any company under the sun has AI in their tagline?

Below is an extract of a 10-page cheat sheet about data science, compiled by Maverick Lin. This cheatsheet is currently a reference in data science that covers basic concepts in probability, statistics, statistical learning, machine learning, deep learning, big data frameworks and SQL. The cheatsheet is loosely based off of The Data Science Design Manual by Steven S. Skiena and An Introduction to Statistical Learning by Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. Inspired by William Chen's The Only Probability Cheatsheet You'll Ever Need, located here.