Imagine waking up one morning to find yourself blind after a lifetime of seeing. This scenario became the reality of thirty-five-year-old Eric Burton, an active and ambitious individual who was in the throes of climbing the corporate ladder. Burton was born with a rare degenerative eye disease called Retinitis Pigmentosa, which caused his vision to fade slowly until one day it disappeared altogether, "like a lightbulb switching off," Burton reflects. He entered a period of darkness, both literally and figuratively, as even the simplest of tasks became daunting to him: leaving the house for a walk, meeting up with friends, ordering food, running errands. Life as he knew it was changed forever.

The recent work of Clark et al. (2018) introduces the AI2 Reasoning Challenge (ARC) and the associated ARC dataset that partitions open domain, complex science questions into an Easy Set and a Challenge Set. That paper includes an analysis of 100 questions with respect to the types of knowledge and reasoning required to answer them; however, it does not include clear definitions of these types, nor does it offer information about the quality of the labels. We propose a comprehensive set of definitions of knowledge and reasoning types necessary for answering the questions in the ARC dataset. Using ten annotators and a sophisticated annotation interface, we analyze the distribution of labels across the Challenge Set and statistics related to them. Additionally, we demonstrate that although naive information retrieval methods return sentences that are irrelevant to answering the query, sufficient supporting text is often present in the (ARC) corpus. Evaluating with human-selected relevant sentences improves the performance of a neural machine comprehension model by 42 points.

Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although the high-quality and domain-specific translation is crucial in the real world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such scenarios. Domain adaptation that leverages both out-of-domain parallel corpora as well as monolingual corpora for in-domain translation, is very important for domain-specific translation. In this paper, we give a comprehensive survey of the state-of-the-art domain adaptation techniques for NMT.

Over years, a crucial part of data-gathering behavior has revolved around what other people think. With the constantly growing popularity and availability of opinion-driven resources such as personal blogs and online review sites, new challenges and opportunities are emerging as people have started using advanced technologies to make decisions now. Sentiment analysis or opinion mining, refers to the use of computational linguistics, text analytics and natural language processing to identify and extract information from source materials. Sentiment analysis is considered one of the most popular applications of text analytics. The primary aspect of sentiment analysis includes data analysis on the body of the text for understanding the opinion expressed by it and other key factors comprising modality and mood.

Music generation research has grown in popularity over the past decade, thanks to the deep learning revolution that has redefined the landscape of artificial intelligence. In this paper, we propose a novel approach to music generation inspired by musical segment concatenation methods and hash learning algorithms. Given a segment of music, we use a deep recurrent neural network and ranking-based hash learning to assign a forward hash code to the segment to retrieve candidate segments for continuation with matching backward hash codes. The proposed method is thus called Deep Segment Hash Learning (DSHL). To the best of our knowledge, DSHL is the first end-to-end segment hash learning method for music generation, and the first to use pair-wise training with segments of music. We demonstrate that this method is capable of generating music which is both original and enjoyable, and that DSHL offers a promising new direction for music generation research.

Dating and romantic relationships not only play a huge role in our personal lives but also collectively influence and shape society. Today, many romantic partnerships originate from the Internet, signifying the importance of technology and the web in modern dating. In this paper, we present a text-based computational approach for estimating the relationship compatibility of two users on social media. Unlike many previous works that propose reciprocal recommender systems for online dating websites, we devise a distant supervision heuristic to obtain real world couples from social platforms such as Twitter. Our approach, the CoupleNet is an end-to-end deep learning based estimator that analyzes the social profiles of two users and subsequently performs a similarity match between the users. Intuitively, our approach performs both user profiling and match-making within a unified end-to-end framework. CoupleNet utilizes hierarchical recurrent neural models for learning representations of user profiles and subsequently coupled attention mechanisms to fuse information aggregated from two users. To the best of our knowledge, our approach is the first data-driven deep learning approach for our novel relationship recommendation problem. We benchmark our CoupleNet against several machine learning and deep learning baselines. Experimental results show that our approach outperforms all approaches significantly in terms of precision. Qualitative analysis shows that our model is capable of also producing explainable results to users.

The Prentice Hall Essence of Computing Series provides a concise, practical and uniform introduction to the core components of an undergraduate computer science degree. Acknowledging the recent changes within Higher Education, this approach uses a variety of pedagogical tools - case studies, worked examples and self-test questions, to underpin the student's learning. The Essence of Artificial Intelligence provides a concise and accessible introduction to the topic for students with no prior knowledge of AI. Taking a pragmatic approach to the subject, this book de-mystifies and makes AI concrete and transparent. Examples and Algorithms are given throughout and can be sensibly implemented in a range of different languages.

Machines might scare policymakers from Brussels to Washington, but artificial intelligence could yield a significant developmental dividend in the developing world. In African markets, the technology behind Alexa and Siri can be harnessed to diagnose illness or address traffic gridlock. One of the most transformative applications of artificial intelligence (AI) is in financial technology, where global investment has risen 38% over the last year. Machine learning, whereby algorithms make predictions and improve based on large amounts of data, is often relegated to the realm technologists and the elite; but for the two billion unbanked adults worldwide, this technology could light a path out of poverty by helping traditional lenders approve loans using hundreds of non-traditional data points. AI has the capacity to add value at the individual, small business, and the large corporate level alike across Africa.

We consider the transfer of experience samples (i.e., tuples < s, a, s', r >) in reinforcement learning (RL), collected from a set of source tasks to improve the learning process in a given target task. Most of the related approaches focus on selecting the most relevant source samples for solving the target task, but then all the transferred samples are used without considering anymore the discrepancies between the task models. In this paper, we propose a model-based technique that automatically estimates the relevance (importance weight) of each source sample for solving the target task. In the proposed approach, all the samples are transferred and used by a batch RL algorithm to solve the target task, but their contribution to the learning process is proportional to their importance weight. By extending the results for importance weighting provided in supervised learning literature, we develop a finite-sample analysis of the proposed batch RL algorithm. Furthermore, we empirically compare the proposed algorithm to state-of-the-art approaches, showing that it achieves better learning performance and is very robust to negative transfer, even when some source tasks are significantly different from the target task.

Artificial Intelligence, or AI, is empowering people with physical disabilities, allowing them to take charge of their own lives but it's also having a surprising impact on people with neuro-diverse conditions like autism. It's easy to generalise about people on the autism spectrum; they like consistency, take things literally and like routine. They are built to provide consistency. They don't (yet) understand sarcasm and they like logic, a lot. But it's important to remember that although people on the autism spectrum will share certain difficulties, everyone's experience of the condition will be very different.