Establishing unique identities for both humans and end systems has been an active research problem in the security community, giving rise to innovative machine learning-based authentication techniques. Although such techniques offer an automated method to establish identity, they have not been vetted against sophisticated attacks that target their core machine learning technique. This paper demonstrates that mimicking the unique signatures generated by host fingerprinting and biometric authentication systems is possible. We expose the ineffectiveness of underlying machine learning classification models by constructing a blind attack based around the query synthesis framework and utilizing Explainable-AI (XAI) techniques. We launch an attack in under 130 queries on a state-of-the-art face authentication system, and under 100 queries on a host authentication system. We examine how these attacks can be defended against and explore their limitations. XAI provides an effective means for adversaries to infer decision boundaries and provides a new way forward in constructing attacks against systems using machine learning models for authentication.

Recent work has studied the reasons for the remarkable performance of deep neural networks in image classification. We examine batch normalization on the one hand and the dynamical systems view of residual networks on the other hand. Our goal is in understanding the notions of stability and smoothness of the inter-layer propagation of ResNets so as to explain when they contribute to significantly enhanced performance. We postulate that such stability is of importance for the trained ResNet to transfer.

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models (RFM) for multi-agent learning, networks that can learn to make accurate predictions of agents' future behavior in multi-agent environments. Because these models operate on the discrete entities and relations present in the environment, they produce interpretable intermediate representations which offer insights into what drives agents' behavior, and what events mediate the intensity and valence of social interactions. Furthermore, we show that embedding RFM modules inside agents results in faster learning systems compared to non-augmented baselines. As more and more of the autonomous systems we develop and interact with become multi-agent in nature, developing richer analysis tools for characterizing how and why agents make decisions is increasingly necessary. Moreover, developing artificial agents that quickly and safely learn to coordinate with one another, and with humans in shared environments, is crucial. The study of multi-agent systems has received considerable attention in recent years and some of the most advanced autonomous systems in the world today are multi-agent in nature (e.g. assembly lines and warehouse management systems). One of the outstanding challenges in this domain is how to foster coordinated behavior among learning agents.

Spatio-temporal (ST) data, which represent multiple time series data corresponding to different spatial locations, are ubiquitous in real-world dynamic systems, such as air quality readings. Forecasting over ST data is of great importance but challenging as it is affected by many complex factors, including spatial characteristics, temporal characteristics and the intrinsic causality between them. In this paper, we propose a general framework (HyperST-Net) based on hypernetworks for deep ST models. More specifically, it consists of three major modules: a spatial module, a temporal module and a deduction module. Among them, the deduction module derives the parameter weights of the temporal module from the spatial characteristics, which are extracted by the spatial module. Then, we design a general form of HyperST layer as well as different forms for several basic layers in neural networks, including the dense layer (HyperST-Dense) and the convolutional layer (HyperST-Conv). Experiments on three types of real-world tasks demonstrate that the predictive models integrated with our framework achieve significant improvements, and outperform the state-of-the-art baselines as well.

Multi-agent predictive modeling is an essential step for understanding physical, social and team-play systems. Recently, Interaction Networks (INs) were proposed for the task of modeling multi-agent physical systems, INs scale with the number of interactions in the system (typically quadratic or higher order in the number of agents). In this paper we introduce VAIN, a novel attentional architecture for multi-agent predictive modeling that scales linearly with the number of agents. We show that VAIN is effective for multi-agent predictive modeling. Our method is evaluated on tasks from challenging multi-agent prediction domains: chess and soccer, and outperforms competing multi-agent approaches.

The course, recorded at the University of San Francisco as part of the Masters of Science in Data Science curriculum, covers the most important practical foundations for modern machine learning. There are 12 lessons, each of which is around two hours long--a list of all the lessons along with a screenshot from each is at the end of this post. There are some excellent machine learning courses already, most notably the wonderful Coursera course from Andrew Ng. But that course is showing its age now, particularly since it uses Matlab for coursework. This new course uses modern tools and libraries, including python, pandas, scikit-learn, and pytorch.

While deep learning models might not be able to simulate large-scale physical phenomena in the same way purpose-built supercomputers and their application stacks do, there is more research emerging that shows how traditional HPC simulations can be augmented, if not replaced in some parts, by neural networks. An upcoming meeting of the American Physical Society that will focus on fluid dynamics and turbulence will shed light on how and where this happening with a number of presentations focused on how neural nets fit into CFD and other physics-driven simulation areas. Researchers from Los Alamos National Lab compared three deep learning models, generative adversarial networks, LAT-NET, and LSTM against their own observations about homogeneous, isotropic, and stationary turbulence and found that deep learning, "which do not take into account any physics of turbulence explicitly, are impressively good overall when it comes to qualitative description of important features of turbulence." Even still, they add that there are some shortcomings that can be addressed by making corrections to the deep learning frameworks through reinforcement of special features of turbulence that the models do not pick out on their own after training. They will present results from a fully-trained GAN that is able to rapidly draw random samples from the full distribution of possible inflow states without needing to solve the Navier-Stokes equations, eliminating the costly process of spinning up inflow turbulence.

Retailers are rolling out new ways for consumers to look for items online. Forever 21, in particular, is moving beyond text-based online search for its customers with visual search. In an announcement for the feature, Forever 21 President Alex Ok said the technology "bridges the gap" between online and offline worlds, while enabling "customers to search for clothing in the same way they think about it -- using visuals, not words." Forever 21 is not alone in its efforts to integrate the latest in AI: A myriad of merchants are using the technology in new and exciting ways. Some retailers even possess the computing power and storage capacity to treat each customer as an individual rather than part of a segment.

It's hard to miss all the attention and hype artificial intelligence (AI) is getting these days. Everywhere you turn there are articles on a myriad of AI-related topics, such as deep learning, machine learning, cognitive computing, computer vision and natural language processing (NLP). These terms are frequently used interchangeably despite meaning very different things -- a sign that many people still don't understand this field. Every conference or event is now an "AI Summit." More startups are now "AI-based."

The second book is "Deep Learning" by Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Francis Bach (Editor). The book came out in 2016 and is considered one of the best books about Deep Learning. It took more than two and a half years to write this great book, which will explain you all the mathematics you need to deal with the Machine and Deep Learning algorithms later in the book.