Technology has advanced enormously in the 30 years since the introduction of the first Children Act, which shaped the UK's system of child safeguarding. Today a computer-generated analysis – "machine learning" that produces predictive analytics – can help social workers assess the probability of a child coming on to the at-risk register. It can also help show how they might prevent that happening. But with technological advances come dilemmas unimaginable back in 1989. Is it right for social workers to use computers to help promote the welfare of children in need?

The underlying dynamical system carries temporal information from one time step to another and captures potential dependencies among the terms of a sequence. Like other deep neural networks, the weights of an RNN are learned by gradient descent. For the input at a time step to affect the output at a later time step, the gradients must back-propagate through each step. Since a sequence can be quite long, RNNs are prone to suffer from vanishing or exploding gradients as described in (Bengio, Frasconi, and Simard 1993) and (Pas-canu, Mikolov, and Bengio 2013). One consequence of this well-known problem is the difficulty of the network to model input-output dependency over a large number of time steps. There have been many different architectures that are designed to mitigate this problem. The most popular RNN architectures such as LSTMs (Hochreiter and Schmidhu-ber 1997) and GRUs (Cho et al. 2014), incorporate a gating mechanism to explicitly retain or discard information.

More than 200 generic drugs approved by the U.S. Food and Drug Administration for non-cancer indications have shown promise for treating cancer. Due to their long history of safe patient use, low cost, and widespread availability, repurposing of generic drugs represents a major opportunity to rapidly improve outcomes for cancer patients and reduce healthcare costs worldwide. Evidence on the efficacy of non-cancer generic drugs being tested for cancer exists in scientific publications, but trying to manually identify and extract such evidence is intractable. In this paper, we introduce a system to automate this evidence extraction from PubMed abstracts. Our primary contribution is to define the natural language processing pipeline required to obtain such evidence, comprising the following modules: querying, filtering, cancer type entity extraction, therapeutic association classification, and study type classification. Using the subject matter expertise on our team, we create our own datasets for these specialized domain-specific tasks. We obtain promising performance in each of the modules by utilizing modern language modeling techniques and plan to treat them as baseline approaches for future improvement of individual components.

This paper develops a new class of nonconvex regularizers for low-rank matrix recovery. Many regularizers are motivated as convex relaxations of the matrix rank function. Our new factor group-sparse regularizers are motivated as a relaxation of the number of nonzero columns in a factorization of the matrix. These nonconvex regularizers are sharper than the nuclear norm; indeed, we show they are related to Schatten-$p$ norms with arbitrarily small $0 < p \leq 1$. Moreover, these factor group-sparse regularizers can be written in a factored form that enables efficient and effective nonconvex optimization; notably, the method does not use singular value decomposition. We provide generalization error bounds for low-rank matrix completion which show improved upper bounds for Schatten-$p$ norm reglarization as $p$ decreases. Compared to the max norm and the factored formulation of the nuclear norm, factor group-sparse regularizers are more efficient, accurate, and robust to the initial guess of rank. Experiments show promising performance of factor group-sparse regularization for low-rank matrix completion and robust principal component analysis.

Efficient exploration for automatic subgoal discovery is a challenging problem in Hierarchical Reinforcement Learning (HRL). In this paper, we show that intrinsic motivation learning increases the efficiency of exploration, leading to successful subgoal discovery. We introduce a model-free subgoal discovery method based on unsupervised learning over a limited memory of agent's experiences during intrinsic motivation. Additionally, we offer a unified approach to learning representations in model-free HRL.

Ontology Design Patterns (ODPs) have become an established and recognised practice for guaranteeing good quality ontology engineering. There are several ODP repositories where ODPs are shared as well as ontology design methodologies recommending their reuse. Performing rigorous testing is recommended as well for supporting ontology maintenance and validating the resulting resource against its motivating requirements. Nevertheless, it is less than straightforward to find guidelines on how to apply such methodologies for developing domain-specific knowledge graphs. ArCo is the knowledge graph of Italian Cultural Heritage and has been developed by using eXtreme Design (XD), an ODP- and test-driven methodology. During its development, XD has been adapted to the need of the CH domain e.g. gathering requirements from an open, diverse community of consumers, a new ODP has been defined and many have been specialised to address specific CH requirements. This paper presents ArCo and describes how to apply XD to the development and validation of a CH knowledge graph, also detailing the (intellectual) process implemented for matching the encountered modelling problems to ODPs. Relevant contributions also include a novel web tool for supporting unit-testing of knowledge graphs, a rigorous evaluation of ArCo, and a discussion of methodological lessons learned during ArCo development.

Called "the restless genius" by The Wall Street Journal and "the ultimate thinking machine" by Forbes magazine, he was selected as one of the top entrepreneurs by Inc. magazine, which described him as the "rightful heir to Thomas Edison." PBS selected him as one of the "sixteen revolutionaries who made America." Ray was the principal inventor of the first CCD flat-bed scanner, the first omni-font optical character recognition, the first print-to-speech reading machine for the blind, the first text-to-speech synthesizer, the first music synthesizer capable of recreating the grand piano and other orchestral instruments, and the first commercially marketed large-vocabulary speech recognition. Among Ray's many honors, he received a Grammy Award for outstanding achievements in music technology; he is the recipient of the National Medal of Technology, was inducted into the National Inventors Hall of Fame, holds twenty-one honorary Doctorates, and honors from three U.S. presidents. Ray has written five national best-selling books, including New York Times best sellers The Singularity Is Near (2005) and How To Create A Mind (2012). He is Co-Founder and Chancellor of Singularity University and a Director of Engineering at Google heading up a team developing machine intelligence and natural language understanding.

A Configuration-Space Decomposition Scheme for Learning-based Collision Checking Yiheng Han 1, Wang Zhao 1, Jia Pan 2, Zipeng Y e 1, Ran Yi 1 and Y ong-Jin Liu 1† Abstract -- Motion planning for robots of high degrees-of- freedom (DOFs) is an important problem in robotics with sampling-based methods in configuration space C as one popular solution. Recently, machine learning methods have been introduced into sampling-based motion planning methods, which train a classifier to distinguish collision free subspace from in-collision subspace in C . In this paper, we propose a novel configuration space decomposition method and show two nice properties resulted from this decomposition. Using these two properties, we build a composite classifier that works compatibly with previous machine learning methods by using them as the elementary classifiers. Experimental results are presented, showing that our composite classifier outperforms state-of-the-art single-classifier methods by a large margin. A real application of motion planning in a multi-robot system in plant phenotyping using three UR5 robotic arms is also presented. I. INTRODUCTION Motion planning plays an important role in robotics, which finds a collision-free path to move a robot from a source to a target position.

A new measure of generalisation error called Off Training Set (OTS) er ror was introduced recently in [Wolpert, 1996b, Wolpert, 1996a]. Under quit e weak assumptions it was shown that with respect to OTS error there are no a priori distinctions between learning algorithms, at least if it is assumed that the target functions are uniformly distributed. Thus, as far as OTS error is co ncerned, an algorithm that minimizes error on the training set will do no better tha n random guessing. If OTS error accurately models the concept of generaliz ation then this is a depressing conclusion indeed. However, in this paper it is argued that OTS error does not model wh at is normally meant by generalization error. In particular, it is shown th at the assumptions underlying one of the main "no free lunch" (NFL) theor ems (theorem 2) in [Wolpert, 1996b] imply that the distributions used to genera te training data and testing data have disjoint supports. Thus, training a neu ral network to recognise faces by showing it images of handwrittten character s is the kind of learning problem covered by the NFL theorem.

Advances in computer vision have brought us to the point where we have the ability to synthesise realistic fake content. Such approaches are seen as a source of disinformation and mistrust, and pose serious concerns to governments around the world. Convolutional Neural Networks (CNNs) demonstrate encouraging results when detecting fake images that arise from the specific type of manipulation they are trained on. However, this success has not transitioned to unseen manipulation types, resulting in a significant gap in the line-of-defense. We propose a Hierarchical Memory Network (HMN) architecture, which is able to successfully detect faked faces by utilising knowledge stored in neural memories as well as visual cues to reason about the perceived face and anticipate its future semantic embeddings. This renders a generalisable face tampering detection framework. Experimental results demonstrate the proposed approach achieves superior performance for fake and fraudulent face detection compared to the state-of-the-art.