Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin softmax (L-Softmax) loss which explicitly encourages intra-class compactness and inter-class separability between learned features. Moreover, L-Softmax not only can adjust the desired margin but also can avoid overfitting. We also show that the L-Softmax loss can be optimized by typical stochastic gradient descent. Extensive experiments on four benchmark datasets demonstrate that the deeply-learned features with L-softmax loss become more discriminative, hence significantly boosting the performance on a variety of visual classification and verification tasks.

Achieving superhuman playing level by AlphaGo corroborated the capabilities of convolutional neural architectures (CNNs) for capturing complex spatial patterns. This result was to a great extent due to several analogies between Go board states and 2D images CNNs have been designed for, in particular translational invariance and a relatively large board. In this paper, we verify whether CNN-based move predictors prove effective for Othello, a game with significantly different characteristics, including a much smaller board size and complete lack of translational invariance. We compare several CNN architectures and board encodings, augment them with state-of-the-art extensions, train on an extensive database of experts' moves, and examine them with respect to move prediction accuracy and playing strength. The empirical evaluation confirms high capabilities of neural move predictors and suggests a strong correlation between prediction accuracy and playing strength. The best CNNs not only surpass all other 1-ply Othello players proposed to date but defeat (2-ply) Edax, the best open-source Othello player.

In Lecture 14 we move from supervised learning to reinforcement learning (RL), in which an agent must learn to interact with an environment in order to maximize its reward. We discuss different algorithms for reinforcement learning including Q-Learning, policy gradients, and Actor-Critic. We show how deep reinforcement learning has been used to play Atari games and to achieve super-human Go performance in AlphaGo. Core to many of these applications are visual recognition tasks such as image classification, localization and detection. Recent developments in neural network (aka "deep learning") approaches have greatly advanced the performance of these state-of-the-art visual recognition systems.

Welcome to the User Guide for the Deep Learning AMI. The Deep Learning AMI (DLAMI) is your one-stop shop for deep learning in the cloud. This customized machine instance is available in most Amazon EC2 regions for a variety of instance types, from a small CPU-only instance to the latest high-powered multi-GPU instances. It comes preconfigured with NVIDIA CUDA and NVIDIA cuDNN, as well as the latest releases of the most popular deep learning frameworks. This guide will help you launch and use the DLAMI.

Artificial Intelligence techniques such as "deep learning" and "convolutional neural networks" have made stunning advancements in image recognition, self-driving cars, and other difficult tasks. Numerous AI companies have appeared to catch the wave of excitement as funding and acquisitions have accelerated. Yet, leading AI researchers realize something is not right. Despite the impressive progress, current AI techniques are limited. For example, deep learning networks typically require millions of training examples before they start working correctly, while a human can learn something new with just a few exposures.

Arthur C. Clarke famously stated that "any sufficiently advanced technology is indistinguishable from magic." No current technology embodies this statement more than neural networks and deep learning. And like any good magic it not only dazzles and inspires but also puts fear into people's hearts. One known property of artificial neural networks (ANNs) is that they are universal function approximators. This means that any mathematical function can be represented by a neural network.

There is a struggle today for the heart and minds of Artificial Intelligence. It's a complex "Game of Thrones" conflict that involves many houses (or tribes) (see: "The Many Tribes of AI"). The two waring factions I focus on today is those who practice Cargo Cult science in the form of Bayesian statistics and those who practice alchemy in the form of experimental Deep Learning. For the uninitiated, let's talk about what Cargo Cult science means. Cargo Cult science is a phrased coined by Richard Feynman to illustrate a practice of in science of not working from fundamentally sound first principles.

We are seeking excellent candidates with interests in Artificial Intelligence (AI), machine learning and deep learning who want to study at a top 10 UK research-led University whilst working with industrial partners. This project is part of the EPSRC Centre for Doctoral Training in Embedded Intelligence. In choosing this project you'll work alongside academics that are leaders in their field and benefit from a four-year studentship award that includes an enhanced EPSRC tax-free annual stipend of at least £17,553 per annum and UK/EU tuition fees. Furthermore, you will have access to a personal training budget of £10,000, which is in addition to a research budget and support from academic members of staff and industrial partners. Loughborough University aims to ensure equality for men and women.

Are you a talented Data Scientist? Are you seeking an opportunity to work on exciting Machine Learning projects? Do Are you currently working in Singapore, holding a work visa? A cool and innovative Machine Learning company are rapidly expanding their in-house research and consulting teams and are seeking to recruit a number of Senior Data Scientists. Your role will be to help design and develop new proof of concepts for enterprise-scale organisations who are seeking to enhance their AI/Deep Learning capabilities.

Bidirectional recursive neural networks(RNN) are really just putting two independent RNNs together. The input sequence is fed in normal time order for one network, and in reverse time order for another. The outputs of the two networks are usually concatenated at each time step, though there are other options, e.g. This structure allows the networks to have both backward and forward information about the sequence at every time step. The concept seems easy enough.