In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a new layer to perform (soft) local reordering of input sequences. Different from existing neural machine translation (NMT) approaches, NPMT does not use attention-based decoding mechanisms. Instead, it directly outputs phrases in a sequential order and can decode in linear time. Our experiments show that NPMT achieves superior performances on IWSLT 2014 German-English/English-German and IWSLT 2015 English-Vietnamese machine translation tasks compared with strong NMT baselines. We also observe that our method produces meaningful phrases in output languages.

Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within a trained CNN model (in the case of image data), and reusing it for other purposes is a field of interest, as it provides access to the visual descriptors previously learnt by the CNN after processing millions of images, without requiring an expensive training phase. Contributions to this field (commonly known as feature representation transfer or transfer learning) have been purely empirical so far, extracting all CNN features from a single layer close to the output and testing their performance by feeding them to a classifier. This approach has provided consistent results, although its relevance is limited to classification tasks. In a completely different approach, in this paper we statistically measure the discriminative power of every single feature found within a deep CNN, when used for characterizing every class of 11 datasets. We seek to provide new insights into the behavior of CNN features, particularly the ones from convolutional layers, as this can be relevant for their application to knowledge representation and reasoning. Our results confirm that low and middle level features may behave differently to high level features, but only under certain conditions. We find that all CNN features can be used for knowledge representation purposes both by their presence or by their absence, doubling the information a single CNN feature may provide. We also study how much noise these features may include, and propose a thresholding approach to discard most of it. All these insights have a direct application to the generation of CNN embedding spaces.

Advances in deep reinforcement learning have allowed autonomous agents to perform well on Atari games, often outperforming humans, using only raw pixels to make their decisions. However, most of these games take place in 2D environments that are fully observable to the agent. In this paper, we present the first architecture to tackle 3D environments in first-person shooter games, that involve partially observable states. Typically, deep reinforcement learning methods only utilize visual input for training. We present a method to augment these models to exploit game feature information such as the presence of enemies or items, during the training phase. Our model is trained to simultaneously learn these features along with minimizing a Q-learning objective, which is shown to dramatically improve the training speed and performance of our agent. Our architecture is also modularized to allow different models to be independently trained for different phases of the game. We show that the proposed architecture substantially outperforms built-in AI agents of the game as well as average humans in deathmatch scenarios.

We introduce contextual explanation networks (CENs)---a class of models that learn to predict by generating and leveraging intermediate explanations. CENs are deep networks that generate parameters for context-specific probabilistic graphical models which are further used for prediction and play the role of explanations. Contrary to the existing post-hoc model-explanation tools, CENs learn to predict and to explain jointly. Our approach offers two major advantages: (i) for each prediction, valid instance-specific explanations are generated with no computational overhead and (ii) prediction via explanation acts as a regularization and boosts performance in low-resource settings. We prove that local approximations to the decision boundary of our networks are consistent with the generated explanations. Our results on image and text classification and survival analysis tasks demonstrate that CENs are competitive with the state-of-the-art while offering additional insights behind each prediction, valuable for decision support.

MLPs (Multi-Layer Perceptrons) are great for many classification and regression tasks. However, it is hard for MLPs to do classification and regression on sequences. In this Python deep learning tutorial, a GRU is implemented in TensorFlow. Tensorflow is one of the many Python Deep Learning libraries. By the way, another great article on Machine Learning is this article on Machine Learning fraud detection.

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)

YOKOHAMA – The Kanagawa Prefectural Police plan to become the first in the nation to introduce predictive policing, a method of anticipating crimes and accidents using artificial intelligence, sources said Sunday. The Kanagawa police will seek research expenses under the prefecture's budget for fiscal 2018 starting April, hoping to put a predictive policing system in place on a trial basis before the 2020 Tokyo Olympics, prefectural government sources said. A system that can determine whether a single perpetrator is behind several crimes, predict an offender's next move and detect where and when crimes or accidents are likely to occur would help police officers investigate crimes and prevent some from happening, they said. It would allow them to patrol the suggested places at the most likely times to ensure safety and would also help speed up probes, the sources said. The AI-based system would employ a "deep learning" algorithm that allows the computer to teach itself by analyzing big data.

Game theory is a field of mathematics that is used to analyse the strategies used by decision makers in competitive situations. It can apply to humans, animals, and computers in various situations but is commonly used in AI research to study "multi-agent" environments where there is more than one system, for example several household robots cooperating to clean the house. Traditionally, the evolutionary dynamics of multi-agent systems have been analysed using simple, symmetric games, such as the classic Prisoner's Dilemma, where each player has access to the same set of actions. Although these games can provide useful insights into how multi-agent systems work and tell us how to achieve a desirable outcome for all players - known as the Nash equilibrium - they cannot model all situations. Our new technique allows us to quickly and easily identify the strategies used to find the Nash equilibrium in more complex asymmetric games - characterised as games where each player has different strategies, goals and rewards.

I got the chance to read this paper on Distributional Bellman published by DeepMind in July. Glossing over it the first time, my impression was that it would be an important paper, since the theory was sound and the experimental results were promising. However, it did not generate as much noise in the reinforcement learning community as I would have hoped. Nevertheless, as I thought the idea of Distributional Bellman was pretty neat, I decided to implement it (in Keras) and test it out myself. I hope this article can help interested readers better understanding the core concepts of Distributional Bellman. To understand Distributional Bellman, we first have to acquire a basic understanding of Q Learning.

When approaching problems with sequential data, such as natural language tasks, recurrent neural networks (RNNs) typically top the choices. While the temporal nature of RNNs are a natural fit for these problems with text data, convolutional neural networks (CNNs), which are tremendously successful when applied to vision tasks, have also demonstrated efficacy in this space. In our LSTM tutorial, we took an in-depth look at how long short-term memory (LSTM) networks work and used TensorFlow to build a multi-layered LSTM network to model stock market sentiment from social media content. In this post, we will briefly discuss how CNNs are applied to text data while providing some sample TensorFlow code to build a CNN that can perform binary classification tasks similar to our stock market sentiment model. We see a sample CNN architecture for text classification in Figure 1.