Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

Attention Is All You Need

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge. Instead of exploiting man-made input features carefully optimized for each task, our system learns internal representations on the basis of vast amounts of mostly unlabeled training data. This work is then used as a basis for building a freely available tagging system with good performance and minimal computational requirements.

/pdf/natural-language-processing-almost-from-scratch-osj5vem4f3.pdf

Natural Language Processing (Almost) from Scratch

We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity tags, semantic roles, semantically similar words and the likelihood that the sentence makes sense (grammatically and semantically) using a language model. The entire network is trained jointly on all these tasks using weight-sharing, an instance of multitask learning. All the tasks use labeled data except the language model which is learnt from unlabeled text and represents a novel form of semi-supervised learning for the shared tasks. We show how both multitask learning and semi-supervised learning improve the generalization of the shared tasks, resulting in state-of-the-art-performance.

/pdf/a-unified-architecture-for-natural-language-processing-deep-qlgoz5mygc.pdf

A unified architecture for natural language processing: deep neural networks with multitask learning

Thermally activated time-delayed message systems

L'invention concerne des procedes et des kits de marquage et de manipulation d'un circuit cellulaire. Les procedes comprennent la transfection d'une cellule de premier ordre dans le circuit cellulaire avec une molecule d'acide nucleique codant pour un ligand captif, et d'une cellule de second ordre dans le circuit cellulaire avec une molecule d'acide nucleique codant pour un recepteur et un polypeptide de fusion effecteur, une molecule d'acide nucleique codant pour un inter-acteur de recepteur et un polypeptide de fusion de protease, et une molecule d'acide nucleique codant pour un gene rapporteur/modificateur.

Procédés de marquage et de manipulation d'un circuit cellulaire

We present a novel method for injecting temporality into entailment graphs to address the problem of spurious entailments, which may arise from similar but temporally distinct events involving the same pair of entities. We focus on the sports domain in which the same pairs of teams play on different occasions, with different outcomes. We present an unsupervised model that aims to learn entailments such as win/lose $\rightarrow$ play, while avoiding the pitfall of learning non-entailments such as win $\not\rightarrow$ lose. We evaluate our model on a manually constructed dataset, showing that incorporating time intervals and applying a temporal window around them, are effective strategies.

Incorporating Temporal Information in Entailment Graph Mining

This paper considers target localization from ambient radio frequency (RF) signals transmitted by the target. We consider a new practical scenario with an array of asynchronous receivers deployed at arbitrary locations, and present an algorithm that jointly locates the target and self-locates the receivers. The approach exploits time-difference-of-arrival (TDoA) between multipath components (multipath TDoA) at each receiver. We derive lower bounds for the localization errors of all the target and receiver locations. The performance is verified numerically and demonstrated experimentally with a hardware implementation that was tested in an anechoic chamber using passive IEEE 802.11ac receivers. We have shown that sub-meter level accuracy can be achieved using 6 static receivers.

Passive Target Localization by Asynchronous Self-Locating Receivers in Multipath Environments

There has been considerable work on syntactic language models and they have advanced greatly over the last decade. Most of them have used a probabilistic contextfree grammar (PCFG) or a dependency grammar (DG). In particular, DG has attracted more and more interest in the past years since dependency parsing has achieved great success. While much work has evaluated the effects of different dependency representations in the context of parsing, there has been relatively little investigation into them on a syntactic language model. In this work, we conduct the first assessment of three dependency representations on a transition-based dependency parsing language model. We show that the choice of dependency representation has an impact on overall performance from the perspective of language modelling.

Mark Johnson

Papers

Thermally activated time-delayed message systems

Procédés de marquage et de manipulation d'un circuit cellulaire

Incorporating Temporal Information in Entailment Graph Mining

Passive Target Localization by Asynchronous Self-Locating Receivers in Multipath Environments

The Effect of Dependency Representation Scheme on Syntactic Language Modelling