CheXNet Keras This project is a tool to build CheXNet-like models, written in Keras. MADDPG An implementation of Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. Aurora Minimal Deep Learning library is written in Python/Cython/C and Numpy/CUDA/cuDNN. Like to add your project?

This nonlinear classification can certainly be done with complicated mathematical equations. However, a simple neural network can do this without a sweat. If the inputs are simplified to binary inputs, 1 or 0, the graph is also simplified as shown on the right hand side. To make the nonlinear classification in neural network. It consists of an input layer as a column, and one or more hidden layers in the middle, and an output layer on the right hand side.

Artificial Intelligence (AI) has entered our daily lives like never before and we are yet to unravel the many other ways in which it could flourish. All tech giants such as Microsoft, Uber, Google, Facebook, Apple, Amazon, Oracle, Intel, IBM or Twitter are competing in the race to lead the market and acquire the most innovative and promising AI businesses. AI is already being used in everyday life with applications including speech recognition, smart cars, fraud detection, security surveillance, music recommendations and AI-powered personal virtual assistant such as Cortana (Microsoft), Siri (Apple) or Alexa (Amazon). Discussions on AI are generally dappled with the terms, 'Machine Learning' and'Deep Learning'. Moreover, they are often interchangeably used.

Every decade seems to have its technological buzzwords: we had personal computers in 1980s; Internet and worldwide web in 1990s; smart phones and social media in 2000s; and Artificial Intelligence (AI) and Machine Learning in this decade. Over the past decade, the field of artificial intelligence (AI) has seen striking developments. As surveyed in [141], there now exist over twenty domains in which AI programs are performing at least as well as (if not better than) humans. These advances have led to a massive burst of excitement in AI that is highly reminiscent of the one that took place during the 1956-1973 boom phase of the first AI hype cycle [56]. Investors are funding billions of dollars in AI-based research and startups [143,144,145], and futurists are again beginning to make alarming predictions about the incipience of powerful AI [149,150,151,152].

Optimal Transport (OT) is a mathematical gem at the interface between probability, analysis and optimization. The goal of that theory is to define geometric tools that are useful to compare probability distributions. Earlier contributions originated from Monge's work in the 18th century, to be later rediscovered under a different formalism by Tolstoi in the 1920's, Kantorovich, Hitchcock and Koopmans in the 1940's. The problem was solved numerically by Dantzig in 1949 and others in the 1950's within the framework of linear programming, paving the way for major industrial applications in the second half of the 20th century. OT was later rediscovered under a different light by analysts in the 90's, following important work by Brenier and others, as well as in the computer vision/graphics fields under the name of earth mover's distances. Recent years have witnessed yet another revolution in the spread of OT, thanks to the emergence of approximate solvers that can scale to sizes and dimensions that are relevant to data sciences. Thanks to this newfound scalability, OT is being increasingly used to unlock various problems in imaging sciences (such as color or texture processing), computer vision and graphics (for shape manipulation) or machine learning (for regression,classification and density fitting). This short book reviews OT with a bias toward numerical methods and their applications in data sciences, and sheds lights on the theoretical properties of OT that make it particularly useful for some of these applications.

Generative adversarial networks (GAN) have been effective for learning generative models for real-world data. However, existing GANs (GAN and its variants) tend to suffer from training problems such as instability and mode collapse. In this paper, we propose a novel GAN framework called evolutionary generative adversarial networks (E-GAN) for stable GAN training and improved generative performance. Unlike existing GANs, which employ a pre-defined adversarial objective function alternately training a generator and a discriminator, we utilize different adversarial training objectives as mutation operations and evolve a population of generators to adapt to the environment (i.e., the discriminator). We also utilize an evaluation mechanism to measure the quality and diversity of generated samples, such that only well-performing generator(s) are preserved and used for further training. In this way, E-GAN overcomes the limitations of an individual adversarial training objective and always preserves the best offspring, contributing to progress in and the success of GANs. Experiments on several datasets demonstrate that E-GAN achieves convincing generative performance and reduces the training problems inherent in existing GANs.

In this paper, we present a theoretical framework for understanding vector embedding, a fundamental building block of many deep learning models, especially in NLP. We discover a natural unitary-invariance in vector embeddings, which is required by the distributional hypothesis. This unitary-invariance states the fact that two embeddings are essentially equivalent if one can be obtained from the other by performing a relative-geometry preserving transformation, for example a rotation. This idea leads to the Pairwise Inner Product (PIP) loss, a natural unitary-invariant metric for the distance between two embeddings. We demonstrate that the PIP loss captures the difference in functionality between embeddings. By formulating the embedding training process as matrix factorization under noise, we reveal a fundamental bias-variance tradeoff in dimensionality selection. With tools from perturbation and stability theory, we provide an upper bound on the PIP loss using the signal spectrum and noise variance, both of which can be readily inferred from data. Our framework sheds light on many empirical phenomena, including the existence of an optimal dimension, and the robustness of embeddings against over-parametrization. The bias-variance tradeoff of PIP loss explicitly answers the fundamental open problem of dimensionality selection for vector embeddings.

Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. Recently, the efficiency of the block coordinate descent (BCD) type methods has been empirically illustrated for DNN training. The main idea of BCD is to decompose the highly composite and nonconvex DNN training problem into several almost separable simple subproblems. However, their convergence property has not been thoroughly studied. In this paper, we establish some unified global convergence guarantees of BCD type methods for a wide range of DNN training models, including but not limited to multilayer perceptrons (MLPs), convolutional neural networks (CNNs) and residual networks (ResNets). This paper nontrivially extends the existing convergence results of nonconvex BCD from the smooth case to the nonsmooth case. Our convergence analysis is built upon the powerful Kurdyka-{\L}ojasiewicz (KL) framework but some new techniques are introduced, including the establishment of the KL property of the objective functions of many commonly used DNNs, where the loss function can be taken as squared, hinge and logistic losses, and the activation function can be taken as rectified linear units (ReLUs), sigmoid and linear link functions. The efficiency of BCD method is also demonstrated by a series of exploratory numerical experiments.

Preconditioned gradient methods are among the most general and powerful tools in optimization. However, preconditioning requires storing and manipulating prohibitively large matrices. We describe and analyze a new structure-aware preconditioning algorithm, called Shampoo, for stochastic optimization over tensor spaces. Shampoo maintains a set of preconditioning matrices, each of which operates on a single dimension, contracting over the remaining dimensions. We establish convergence guarantees in the stochastic convex setting, the proof of which builds upon matrix trace inequalities. Our experiments with state-of-the-art deep learning models show that Shampoo is capable of converging considerably faster than commonly used optimizers. Although it involves a more complex update rule, Shampoo's runtime per step is comparable to that of simple gradient methods such as SGD, AdaGrad, and Adam.

The easiness at which adversarial instances can be generated in deep neural networks raises some fundamental questions on their functioning and concerns on their use in critical systems. In this paper, we draw a connection between over-generalization and adversaries: a possible cause of adversaries lies in models designed to make decisions all over the input space, leading to inappropriate high-confidence decisions in parts of the input space not represented in the training set. We empirically show an augmented neural network, which is not trained on any types of adversaries, can increase the robustness by detecting black-box one-step adversaries, i.e. assimilated to out-distribution samples, and making generation of white-box one-step adversaries harder.