Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away connections or hidden units. But standard training does not necessarily encourage nets to be amenable to pruning. We introduce targeted dropout, a method for training a neural network so that it is robust to subsequent pruning. Before computing the gradients for each weight update, targeted dropout stochastically selects a set of units or weights to be dropped using a simple self-reinforcing sparsity criterion and then computes the gradients for the remaining weights. The resulting network is robust to post hoc pruning of weights or units that frequently occur in the dropped sets. The method improves upon more complicated sparsifying regularisers while being simple to implement and easy to tune.

Differential Private Learning and Online Learning are two well-studied areas in machine learning. While at a first glance these two subjects may seem disparate, recent works gathered a growing amount of evidence which suggests otherwise. For example, Adaptive Data Analysis [15, 14, 24, 19, 3] shares strong similarities with adversarial frameworks studied in online learning, and on the other hand exploits ideas and tools from differential privacy. A more formal relation between private and online learning is manifested by the following fact: Every privately learnable class is online learnable. This implication and variants of it were derived by several recent works [20, 9, 1] (see the related work section for more details). One caveat of the latter results is that they are non-constructive: they show that every privately learnable class has a finite Littlestone dimension. Then, since the Littlestone dimension is known to capture online learnability [26, 5], it follows that privately learnable classes are indeed online learnable. Consequently, the implied online learner is not necessarily efficient, even if the assumed private learner is.

In recent years, deep reinforcement learning has pushed the boundaries of Artificial Intelligence to an unprecedented level, achieving what was expected to be possible only in a decade and outperforming human intelligence in a number of highly complex tasks. Paramount examples of this potential have appeared over the past few years, with such algorithms mastering games and tasks of increasing complexity, from playing Atari to learning to walk and beating world grandmasters at the game of Go [16, 23, 24, 31-33]. Such impressive success would be impossible without using neural networks to approximate value functions and / or policy functions in reinforcement learning algorithms. While neural networks, in particular deep neural networks, provide a powerful and versatile tool to approximate high dimensional functions [4, 12, 17], their intrinsic nonlinearity might also lead to trouble in training, in particular in the context of reinforcement learning. For example, it is well known that nonlinear approximation to value function might cause divergence in the classical temporal-difference learning due to instability [40].

We show that under mild conditions, Estimation of Distribution Algorithms (EDAs) can be written as variational Expectation-Maximization (EM) that uses a mixture of weighted particles as the approximate posterior. In the infinite particle limit, EDAs can be viewed as exact EM. Because EM sits on a rigorous statistical foundation and has been thoroughly analyzed, this connection provides a coherent framework with which to reason about EDAs. Importantly, the connection also suggests avenues for possible improvements to EDAs owing to our ability to leverage general statistical tools and generalizations of EM. For example, we make use of results about known EM convergence properties to propose an adaptive, hybrid EDA-gradient descent algorithm; this hybrid demonstrates better performance than either component of the hybrid on several canonical, non-convex test functions. We also demonstrate empirically that although one might hypothesize that reducing the variational gap could prove useful, it actually degrades performance of EDAs. Finally, we show that the connection between EM and EDAs provides us with a new perspective on why EDAs are performing approximate natural gradient descent.

We present an alternative layer to convolution layers in convolutional neural networks (CNNs). Our approach reduces the complexity of convolutions by replacing it with binary decisions. Those binary decisions are used as indexes to conditional probability distributions where each probability represents a leaf in a decision tree. This means that only the indices to the probabilities need to be determined once, thus reducing the complexity of convolutions by the depth of the output tensor. Index computation is performed by simple binary decisions that require fewer CPU cycles compared to conventionally used multiplications. In addition, we show how convolutions can be replaced by binary decisions. These binary decisions form indices in the conditional probability distributions and we show how they are used to replace 2D weight matrices as well as 3D weight tensors. These new layers can be trained like convolution layers in CNNs based on the backpropagation algorithm, for which we provide a formalization. Our results on multiple publicly available data sets show that our approach outperforms conventional CNNs. Beyond the formalized reduction of complexity and the improved qualitative performance, we show empirically a significant runtime improvement compared to convolution layers. DOWNLOAD EXAMPLES: https://drive.google.com/open?id=1gqLD5N--tqVNCixenXiptcaR5hAP5IYJ

Many tasks such as retrieval and recommendations can significantly benefit from structuring the data, commonly in a hierarchical way. To achieve this through annotations of high dimensional data such as images or natural text can be significantly labor intensive. We propose an approach for uncovering the hierarchical structure of data based on efficient discriminative testing rather than annotations of individual datapoints. Using two-alternative-forced-choice (2AFC) testing and deep metric learning we achieve embedding of the data in semantic space where we are able to successfully hierarchically cluster. We actively select triplets for the 2AFC test such that the modeling process is highly efficient with respect to the number of tests presented to the annotator. We empirically demonstrate the feasibility of the method by confirming the shape bias on synthetic data and extract hierarchical structure on the Fashion-MNIST dataset to a finer granularity than the original labels.

We study the problem of embedding-based entity alignment between knowledge graphs (KGs). Previous works mainly focus on the relational structure of entities. Some further incorporate another type of features, such as attributes, for refinement. However, a vast of entity features are still unexplored or not equally treated together, which impairs the accuracy and robustness of embedding-based entity alignment. In this paper, we propose a novel framework that unifies multiple views of entities to learn embeddings for entity alignment. Specifically, we embed entities based on the views of entity names, relations and attributes, with several combination strategies. Furthermore, we design some cross-KG inference methods to enhance the alignment between two KGs. Our experiments on real-world datasets show that the proposed framework significantly outperforms the state-of-the-art embedding-based entity alignment methods. The selected views, cross-KG inference and combination strategies all contribute to the performance improvement.

The advantages offered by the presence of a schema are numerous. However, many XML documents in practice are not accompanied by a (valid) schema, making schema inference an attractive research problem. The fundamental task in XML schema learning is inferring restricted subclasses of regular expressions. Most previous work either lacks support for interleaving or only has limited support for interleaving. In this paper, we first propose a new subclass Single Occurrence Regular Expressions with Interleaving (SOIRE), which has unrestricted support for interleaving. Then, based on single occurrence automaton and maximum independent set, we propose an algorithm iSOIRE to infer SOIREs. Finally, we further conduct a series of experiments on real datasets to evaluate the effectiveness of our work, comparing with both ongoing learning algorithms in academia and industrial tools in real-world. The results reveal the practicability of SOIRE and the effectiveness of iSOIRE, showing the high preciseness and conciseness of our work.

Intelligent Personal Assistants (IPAs) are software agents that can perform tasks on behalf of individuals and assist them on many of their daily activities. IPAs capabilities are expanding rapidly due to the recent advances on areas such as natural language processing, machine learning, artificial cognition, and ubiquitous computing, which equip the agents with competences to understand what users say, collect information from everyday ubiquitous devices (e.g., smartphones, wearables, tablets, laptops, cars, household appliances, etc.), learn user preferences, deliver data-driven search results, and make decisions based on user's context. Apart from the inherent complexity of building such IPAs, developers and researchers have to address many critical architectural challenges (e.g., low-latency, scalability, concurrency, ubiquity, code mobility, interoperability, support to cognitive services and reasoning, to name a few.), thereby diverting them from their main goal: building IPAs. Thus, our contribution in this paper is twofold: 1) we propose an architecture for a platform-agnostic, high-performance, ubiquitous, and distributed middleware that alleviates the burdensome task of dealing with low-level implementation details when building IPAs by adding multiple abstraction layers that hide the underlying complexity; and 2) we present an implementation of the middleware that concretizes the aforementioned architecture and allows the development of high-level capabilities while scaling the system up to hundreds of thousands of IPAs with no extra effort. We demonstrate the powerfulness of our middleware by analyzing software metrics for complexity, effort, performance, cohesion and coupling when developing a conversational IPA.

Automated text generation has been applied broadly in many domains such as marketing and robotics, and used to create chatbots, product reviews and write poetry. The ability to synthesize text, however, presents many potential risks, while access to the technology required to build generative models is becoming increasingly easy. This work is aligned with the efforts of the United Nations and other civil society organisations to highlight potential political and societal risks arising through the malicious use of text generation software, and their potential impact on human rights. As a case study, we present the findings of an experiment to generate remarks in the style of political leaders by fine-tuning a pretrained AWD- LSTM model on a dataset of speeches made at the UN General Assembly. This work highlights the ease with which this can be accomplished, as well as the threats of combining these techniques with other technologies.