Recently we've been seeing computers playing games against humans, either as bots in multiplayer games or as opponents in one-on-one games like Dota2, PUB-G, Mario. Deepmind(a research company) made history when the news that their AlphaGo program defeated the South Korean Go world champion in 2016. If you're an intense gamer, probably you must have listened about Dota 2 OpenAI Five match, where machines played against humans and defeated world top Dota2 players in few matches (If you are interested about this, here is the complete analysis of the algorithm and the game played by the machine). So here's the central question, Why do we need reinforcement learning? Is it only used for games?

Silicon Valley giants such as Google and Facebook have been trying to harness artificial intelligence by training brain-inspired neural networks to better represent the real world. Digital Reasoning, a cognitive computing company based in Franklin, Tenn., recently announced that it has trained a neural network consisting of 160 billion parameters--more than 10 times larger than previous neural networks. The Digital Reasoning neural network easily surpassed previous records held by Google's 11.2-billion parameter system and Lawrence Livermore National Laboratory's 15-billion parameter system. But it also showed improved accuracy over previous neural networks in tackling an "industry-standard dataset" consisting of 20,000 word analogies. Digital Reasoning's model achieved an accuracy of almost 86 percent; significantly higher than Google's previous record of just over 76 percent and Stanford University's 75 percent. "We are extremely proud of the results we have achieved, and the contribution we are making daily to the field of deep learning," said Matthew Russell, chief technology officer for Digital Reasoning, in a press release.

Want to do Computer Vision? Deep Learning is the way to go these days. Large scale datasets plus the representational power of deep Convolutional Neural Networks (CNNs) make for super accurate and robust models. Only one challenge still remains: how to design your model. The many standard tasks in computer vision all require special consideration: classification, detection, segmentation, pose estimation, enhancement and restoration, and action recognition. Although the state-of-the-art networks used for each of them exhibit common patterns, they'll all still need their own unique design twist.

This resource is part of a series on specific topics related to data science: regression, clustering, neural networks, deep learning, decision trees, ensembles, correlation, Python, R, Tensorflow, SVM, data reduction, feature selection, experimental design, cross-validation, model fitting, and many more. To keep receiving these articles, sign up on DSC. Previous editions, in alphabetical order, can be accessed here: Part 1 Part 2 Part 3 Part 4 Part 5 Part 6 Part 7 Part 8 Part 9. To make sure you keep getting these emails, please add [email protected] to your address book or whitelist us.

Summary: In the literal blink of an eye, image-based AI has gone from high cost, high risk projects to quick and reasonably reliable. C-level execs looking for AI techniques to exploit need to revisit their assumptions and move these up the list. For data scientists these are miraculous times. We tend to think of miracles as something that occurs instantaneously but in our world that's not quite so. Still the rate of change in deep learning, particularly in image recognition is mind boggling and way up there on the miraculous scale.

The growing capabilities of Artificial Intelligence (AI) are changing the world as we know it. Ideas once confined to the imagination are now becoming a reality, with AI technology creating outputs either largely or entirely independent from human intervention. In 2018, an album called I AM AI was the first of its kind to be entirely composed and produced by AI technology, through a music composition software called Amper. Deep learning networks allow Amper to analyse data to learn chords, notes, genres, tempo and song length to independently compose melodies. A qualified person is an Australian citizen or a person resident in Australia.[1]

Our platform supports a large, variable number of agents within a persistent and open-ended task. The inclusion of many agents and species leads to better exploration, divergent niche formation, and greater overall competence. In recent years, multiagent settings have become an effective platform for deep reinforcement learning research. Despite this progress, there are still two main challenges for multiagent reinforcement learning. We need to create open-ended tasks with a high complexity ceiling: current environments are either complex but too narrow or open-ended but too simple.

Driven by the goal to enable sleep apnea monitoring and machine learning-based detection at home with small mobile devices, we investigate whether interpretation-based indirect knowledge transfer can be used to create classifiers with acceptable performance. Interpretation-based indirect knowledge transfer means that a classifier (student) learns from a synthetic dataset based on the knowledge representation from an already trained Deep Network (teacher). We use activation maximization to generate visualizations and create a synthetic dataset to train the student classifier. This approach has the advantage that student classifiers can be trained without access to the original training data. With experiments we investigate the feasibility of interpretation-based indirect knowledge transfer and its limitations. The student achieves an accuracy of 97.8% on MNIST (teacher accuracy: 99.3%) with a similar smaller architecture to that of the teacher. The student classifier achieves an accuracy of 86.1% and 89.5% for a subset of the Apnea-ECG dataset (teacher: 89.5% and 91.1%, respectively).

Time Series forecasting (univariate and multivariate) is a problem of high complexity due the different patterns that have to be detected in the input, ranging from high to low frequencies ones. In this paper we propose a new model for timeseries prediction that utilizes convolutional layers for feature extraction, a recurrent encoder and a linear autoregressive component. We motivate the model and we test and compare it against a baseline of widely used existing architectures for univariate and multivariate timeseries. The proposed model appears to outperform the baselines in almost every case of the multivariate timeseries datasets, in some cases even with 50% improvement which shows the strengths of such a hybrid architecture in complex timeseries.

Anomaly detection algorithms are often thought to be limited because they don't facilitate the process of validating results performed by domain experts. In Contrast, deep learning algorithms for anomaly detection, such as autoencoders, point out the outliers, saving experts the time-consuming task of examining normal cases in order to find anomalies. Most outlier detection algorithms output a score for each instance in the database. The top-k most intense outliers are returned to the user for further inspection; however the manual validation of results becomes challenging without additional clues. An explanation of why an instance is anomalous enables the experts to focus their investigation on most important anomalies and may increase their trust in the algorithm. Recently, a game theory-based framework known as SHapley Additive exPlanations (SHAP) has been shown to be effective in explaining various supervised learning models. In this research, we extend SHAP to explain anomalies detected by an autoencoder, an unsupervised model. The proposed method extracts and visually depicts both the features that most contributed to the anomaly and those that offset it. A preliminary experimental study using real world data demonstrates the usefulness of the proposed method in assisting the domain experts to understand the anomaly and filtering out the uninteresting anomalies, aiming at minimizing the false positive rate of detected anomalies.