A variety of learning objectives have been proposed for training latent variable generative models. We show that many of them, including InfoGAN, ALI/BiGAN, ALICE, CycleGAN, beta-VAE, adversarial autoencoders, AVB, AS-VAE and InfoVAE, are Lagrangian duals of the same primal optimization problem, corresponding to different settings of the Lagrange multipliers. The primal problem optimizes the mutual information between latent and visible variables, subject to the constraints of accurately modeling the data distribution and performing correct amortized inference. Based on this observation, we provide an exhaustive characterization of the statistical and computational trade-offs made by all the training objectives in this class of Lagrangian duals. Next, we propose a dual optimization method where we optimize model parameters as well as the Lagrange multipliers. This method achieves Pareto near-optimal solutions in terms of optimizing information and satisfying the consistency constraints.

What are the functions of curiosity? What are the mechanisms of curiosity-driven learning? We approach these questions about the living using concepts and tools from machine learning and developmental robotics. We argue that curiosity-driven learning enables organisms to make discoveries to solve complex problems with rare or deceptive rewards. By fostering exploration and discovery of a diversity of behavioural skills, and ignoring these rewards, curiosity can be efficient to bootstrap learning when there is no information, or deceptive information, about local improvement towards these problems. We also explain the key role of curiosity for efficient learning of world models. We review both normative and heuristic computational frameworks used to understand the mechanisms of curiosity in humans, conceptualizing the child as a sense-making organism. These frameworks enable us to discuss the bi-directional causal links between curiosity and learning, and to provide new hypotheses about the fundamental role of curiosity in self-organizing developmental structures through curriculum learning. We present various developmental robotics experiments that study these mechanisms in action, both supporting these hypotheses to understand better curiosity in humans and opening new research avenues in machine learning and artificial intelligence. Finally, we discuss challenges for the design of experimental paradigms for studying curiosity in psychology and cognitive neuroscience. Keywords: Curiosity, intrinsic motivation, lifelong learning, predictions, world model, rewards, free-energy principle, learning progress, machine learning, AI, developmental robotics, development, curriculum learning, self-organization.

In this work, we propose an ensemble of classifiers to distinguish between various degrees of abnormalities of the heart using Phonocardiogram (PCG) signals acquired using digital stethoscopes in a clinical setting, for the INTERSPEECH 2018 Computational Paralinguistics (ComParE) Heart Beats Sub-Challenge. Our primary classification framework constitutes a convolutional neural network with 1D-CNN time-convolution (tConv) layers, which uses features transferred from a model trained on the 2016 Physionet Heart Sound Database. We also employ a Representation Learning (RL) approach to generate features in an unsupervised manner using Deep Recurrent Autoencoders and use Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) classifiers. Finally, we utilize an SVM classifier on a high-dimensional segment-level feature extracted using various functionals on short-term acoustic features, i.e., Low-Level Descriptors (LLD). An ensemble of the three different approaches provides a relative improvement of 11.13% compared to our best single subsystem in terms of the Unweighted Average Recall (UAR) performance metric on the evaluation dataset.

In particular, we clarify and make explicit all of the proofs mentioned therein, and provide many more examples to the definitions, in a way that should be helpful to readers approaching abstract argumentation theory for the first time. However, we provide minimal commentary and will refer the reader to Dung's paper for the intuitions behind various concepts. The appropriate mathematical prerequisites are provided in the appendices.

Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of better networks, which results in a complexification of their architectures with more layers, multiple sub-networks, or even the combination of multiple classifiers. In this paper, we show how to redesign a simple network to reach excellent performances, which are better than the results reproduced with CapsNet on several datasets, by replacing a layer with a Hit-or-Miss layer. This layer contains activated vectors, called capsules, that we train to hit or miss a central capsule by tailoring a specific centripetal loss function. We also show how our network, named HitNet, is capable of synthesizing a representative sample of the images of a given class by including a reconstruction network. This possibility allows to develop a data augmentation step combining information from the data space and the feature space, resulting in a hybrid data augmentation process. In addition, we introduce the possibility for HitNet, to adopt an alternative to the true target when needed by using the new concept of ghost capsules, which is used here to detect potentially mislabeled images in the training data.

Not a week goes by that I don't see dozens of headlines blaming "AI" or "deep learning" for yet another ethical conundrum that will doom human society. Whether it is predictive policing or facial recognition or autonomous weapons, it seems nearly every facet of society is facing an "AI revolution" that will destroy humankind. If one peels back the breathless hype and viral buzzwords, however, is it really AI that we are worried about or is it the shift towards a data-centric society with or without deep learning advances? To the general public, "big data" and "deep learning" are increasingly becoming synonymous, fueled by the never-ending hype machine of Silicon Valley and the very legitimate advances occurring in deep learning powered largely by the massive availability of large datasets and the unique abilities of those models to make sense of all that data. From a technical standpoint, however, these are two entirely distinct concepts.

While robotics and artificial intelligence (AI) promise great advances in productivity, mostly they seem to worry people. Commentators talk and write endlessly about how these marvelous technologies will steal jobs from both workers and the managerial class, creating a large unemployed population. If history has anything to say, however, and it does, such fears are not only exaggerated, they are off the mark entirely. Ultimately, AI will create more new jobs than it destroys and likely in occupations heretofore nonexistent. Popular commentary on this matter maintains an almost universally downbeat tone.

Hysteria about the future of artificial intelligence (AI) is everywhere. There is no shortage of sensationalist news about how AI can cure diseases, accelerate human innovation and improve human creativity. From the headlines alone, you would think we already live in a future where AI has infiltrated every aspect of society. While AI has opened up a wealth of promising opportunities, it has also led to a mindset that can be best described as "AI solutionism". This is the attitude that, given enough data, machine learning algorithms can solve all of humanity's problems.

"Rhythmic acrobatic… she's a dynamite attraction," these lines the song, "Dancing Machine", are coming to life in a new video where 2,000 robots and 1,700 factory workers are moving in unison to build a car body in just over one minute. The robot ballet takes place in a SEAT sheet metal workshop in Spain where several different types of dancing machines are featured in the mechanical performance. It isn't just machines, the dancing robots join the efforts of the employees, and final verifications are carried out by the factory workers. People and machines together are able to put together one car body every 68 seconds!

Spirit AI is using artificial intelligence to combat toxic behavior in game communities. The London company has created its Ally social intelligence tool to decipher online conversations and monitor whether cyberbullying is taking place. It is the brainchild of researchers at New York University, according to Mitu Khandaker, creative partnerships director at Spirit AI and an assistant arts professor at the NYU game center. The company uses AI, natural language understanding, and machine learning to help data science and customer service teams to understand the general tenor of an online community. It also helps predict problems before they escalate.