The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are a remarkable demonstration of deep reinforcement learning's capabilities, achieving superhuman performance in the complex game of Go with progressively increasing autonomy. However, many obstacles remain in the understanding of and usability of these promising approaches by the research community. Toward elucidating unresolved mysteries and facilitating future research, we propose ELF OpenGo, an open-source reimplementation of the AlphaZero algorithm. ELF OpenGo is the first open-source Go AI to convincingly demonstrate superhuman performance with a perfect (20:0) record against global top professionals. We apply ELF OpenGo to conduct extensive ablation studies, and to identify and analyze numerous interesting phenomena in both the model training and in the gameplay inference procedures. Our code, models, selfplay datasets, and auxiliary data are publicly available.

Learning sentence vectors from an unlabeled corpus has attracted attention because such vectors can represent sentences in a lower dimensional and continuous space. Simple heuristics using pre-trained word vectors are widely applied to machine learning tasks. However, they are not well understood from a theoretical perspective. We analyze learning sentence vectors from a transfer learning perspective by using a PAC-Bayes bound that enables us to understand existing heuristics. We show that simple heuristics such as averaging and inverse document frequency weighted averaging are derived by our formulation. Moreover, we propose novel sentence vector learning algorithms on the basis of our PAC-Bayes analysis.

In this paper we present a Recurrent neural networks (RNN) based architecture that achieves an AUCROC of 0.9147 for predicting the onset of Congestive Heart Failure (CHF) 15 months in advance using a 12-month observation window on a large cohort of 216,394 patients. We believe this to be the largest study in CHF onset prediction with respect to the number of CHF case patients in the cohort and the test set (3,332 CHF patients) on which the AUC metrics are reported. We explore the extent to which LSTM (Long Short Term Memory) based model, a variant of RNNs, can accurately predict the onset of CHF when compared to known linear baselines like Logistic Regression, Random Forests and deep learning based models such as Multi-Layer Perceptron and Convolutional Neural Networks. We utilize demographics, medical diagnosis and procedure data from 21,405 CHF and 194,989 control patients to as our features. We describe our feature embedding strategy for medical diagnosis codes that accommodates the sparse, irregular, longitudinal, and high-dimensional characteristics of EHR data. We empirically show that LSTMs can capture the longitudinal aspects of EHR data better than the proposed baselines. As an attempt to interpret the model, we present a temporal data analysis-based technique on false positives to attribute feature importance. A model capable of predicting the onset of congestive heart failure months in the future with this level of accuracy and precision can support efforts of practitioners to implement risk factor reduction strategies and researchers to begin to systematically evaluate interventions to potentially delay or avert development of the disease with high mortality, morbidity and significant costs.

Working in high-dimensional latent spaces, the internal encoding of data in Variational Autoencoders becomes naturally sparse. We discuss this known but controversial phenomenon sometimes refereed to as overpruning, to emphasize the under-use of the model capacity. In fact, it is an important form of self-regularization, with all the typical benefits associated with sparsity: it forces the model to focus on the really important features, highly reducing the risk of overfitting. Especially, it is a major methodological guide for the correct tuning of the model capacity, progressively augmenting it to attain sparsity, or conversely reducing the dimension of the network removing links to zeroed out neurons. The degree of sparsity crucially depends on the network architecture: for instance, convolutional networks typically show less sparsity, likely due to the tighter relation of features to different spatial regions of the input.

The cloud radio access network (CRAN) is a promising paradigm to meet the stringent requirements of the fifth generation (5G) wireless systems. Meanwhile, wireless traffic prediction is a key enabler for C-RANs to improve both the spectrum efficiency and energy efficiency through load-aware network managements. This paper proposes a scalable Gaussian process (GP) framework as a promising solution to achieve large-scale wireless traffic prediction in a cost-efficient manner. First, to the best of our knowledge, this paper is the first to empower GP regression with the alternating direction method of multipliers (ADMM) for parallel hyper-parameter optimization in the training phase, where such a scalable training framework well balances the local estimation in baseband units (BBUs) and information consensus among BBUs in a principled way for large-scale executions. Second, in the prediction phase, we fuse local predictions obtained from the BBUs via a cross-validation based optimal strategy, which demonstrates itself to be reliable and robust for general regression tasks. Moreover, such a cross-validation based optimal fusion strategy is built upon a well acknowledged probabilistic model to retain the valuable closed-form GP inference properties. Third, we propose a CRAN based scalable wireless prediction architecture, where the prediction accuracy and the time consumption can be balanced by tuning the number of the BBUs according to the real-time system demands. Experimental results show that our proposed scalable GP model can outperform the state-of-the-art approaches considerably, in terms of wireless traffic prediction performance. I. INTRODUCTION The fifth generation (5G) system is expected to provide approximately 1000 times higher wireless capacity and reduce up to 90 percent of energy consumption compared with the current 4G system [1]. A CRAN is composed of two parts: the distributed remote radio heads (RRHs) with basic radio functionalities to provide coverage over a large area, and the centralized baseband units (BBUs) pool with parallel BBUs to support joint processing and cooperative network management. The BBUs can perform dynamic resource allocation in accordance with realtime networkdemands based on the virtualized resources in cloud computing. One major feature for the C-RANs to enable high energy-efficient services is the fast adaptability to nonuniform traffic variations [1]-[4], e.g., the tidal effects. Consequently, wireless traffic prediction techniques stand out as the key enabler to realize such loadaware managementand proactive control in C-RANs, e.g., the load-aware RRH on/off operation [4].

A new study from China has found that an AI system can best some doctors when it comes to diagnosing common childhood diseases. The study, published in Nature Medicine yesterday (Feb. The study trained a deep-learning system on 101 million data points generated from the electronic records of 1.3 million patient visits to a medical center in Guangzhou. Researchers found that the AI system was able to meet or outperform two groups of junior physicians in accurately diagnosing a range of ailments, from asthma and pneumonia, to sinusitis and mouth-related diseases. The AI was also able to meet or exceed diagnostic performance with some groups of senior physicians, for instance, in the category of upper respiratory issues.

It's a mystery that deep learning works so well. Even though there are several hints about why deep neural networks are so effective, the truth is that nobody is entirely sure and theoretical understanding of deep learning is very much an active area of research. We will make neural networks paint abstract images for us, and then we will interpret those images to develop a better intuition on what might be happening under the hood. Also, as a bonus, by the end of the tutorial, you'll be able to generate images such as the following (everything is less than 100 lines of PyTorch code. This image was generated by a simple architecture called Compositional Pattern Producing Networks (CPPN) which I got introduced to via this blog post. In that blog post, the author generates abstract images via neural networks written in JavaScript.

I usually write about how to integrate and launch ML/AI in consumer-facing products. However, a large part of my job is building ML/AI developer tools, some of which are open sourced. In this field there is a proliferation of startups whose tagline is a random pick from all permutations of the words deep learning, platform, enterprise, deployment, training, scale, democratize. Their offerings span from data acquisition (data annotation by humans) to data science workbench environments and hosted model deployment. After speaking with many startups and investors about deep learning developer tools, I felt that it would be useful to share some of my thoughts more broadly.

Jos Martin, senior engineering manager at data analysis and simulation software company MathWorks, defines an artificial intelligence framework as something for programmers that abstracts elements of complexity. In a post on the Computer Weekly Developer Network (CWDN) blog, Martin says: "As a user of deep learning you don't usually need to go and write training algorithms." For instance, Google's Brain team has developed TensorFlow, Facebook has created PyTorch, Microsoft provides its Cognitive Toolkit, while Amazon Web Services (AWS) offers the MXNet deep learning framework as a service. Martin says there are many different intelligence layer types already implemented in openly available libraries, and as such, developers should really view any single layer of intelligence as a whole set of computing neurons connected together. What these frameworks have in common is that they aim to make it easier for programmers to create AI-powered applications.

This repo is an open-source implementation of DeepMind's Sequential Social Dilemma (SSD) multi-agent game-theoretic environments [1]. SSDs can be thought of as analogous to spatially and temporally extended Prisoner's Dilemma-like games. The reward structure poses a dilemma because individual short-term optimal strategies lead to poor long-term outcomes for the group. The implemented environments are structured to be compatible with OpenAIs gym environments (https://github.com/openai/gym) The above plot shows the empirical Schelling diagrams for both Cleanup (A) and Harvest (B) (from [2]).