The space of graphs is characterized by a non-trivial geometry, which often complicates performing inference in practical applications. A common approach is to use embedding techniques to represent graphs as points in a conventional Euclidean space, but non-Euclidean spaces are often better suited for embedding graphs. Among these, constant curvature manifolds (CCMs), like hyperspheres and hyperboloids, offer a computationally tractable way to compute metric, yet non-Euclidean, geodesic distances. In this paper, we introduce a novel adversarial graph embedding technique to represent graphs on CCMs, and exploit such a mapping for detecting changes in stationarity in a graph-generating process. To this end, we introduce a novel family of change detection tests operating by means of distances on CCMs. We perform experiments on synthetic graph streams, and on sequences of functional networks extracted from iEEG data with the aim of detecting the onset of epileptic seizures. We show that our methods are able to detect extremely small changes in the graph-generating process, consistently outperforming solutions based on Euclidean embeddings. The general nature of our framework highlights its potential to be extended to other applications characterized by graph data or non-Euclidean geometries.

The seminal work of Gatys et al. demonstrated the power of Convolutional Neural Networks (CNN) in creating artistic imagery by separating and recombining image content and style. This process of using CNN to render a content image in different styles is referred to as Neural Style Transfer (NST). Since then, NST has become a trending topic both in academic literature and industrial applications. It is receiving increasing attention and a variety of approaches are proposed to either improve or extend the original NST algorithm. This review aims to provide an overview of the current progress towards NST, as well as discussing its various applications and open problems for future research.

Multimodal features play a key role in wearable sensor-based human activity recognition (HAR). Selecting the most salient features adaptively is a promising way to maximize the effectiveness of multimodal sensor data. In this regard, we propose a "collect fully and select wisely" principle as well as an interpretable parallel recurrent model with convolutional attentions to improve the recognition performance. We first collect modality features and the relations between each pair of features to generate activity frames, and then introduce an attention mechanism to select the most prominent regions from activity frames precisely. The selected frames not only maximize the utilization of valid features but also reduce the number of features to be computed effectively. We further analyze the accuracy and interpretability of the proposed model based on extensive experiments. The results show that our model achieves competitive performance on two benchmarked datasets and works well in real life scenarios.

Dialogue act recognition is an important part of natural language understanding. We investigate the way dialogue act corpora are annotated and the learning approaches used so far. We find that the dialogue act is context-sensitive within the conversation for most of the classes. Nevertheless, previous models of dialogue act classification work on the utterance-level and only very few consider context. We propose a novel context-based learning method to classify dialogue acts using a character-level language model utterance representation, and we notice significant improvement. We evaluate this method on the Switchboard Dialogue Act corpus, and our results show that the consideration of the preceding utterances as a a context of the current utterance improves dialogue act detection.

Because of the dimensionality of the motor space, as well as the infinite possible combinations of successive motor commands, agents need compact representations that capture the structure of the resulting displacements. In the case of an autonomous agent with no a priori knowledge about its sensorimotor apparatus, this compression has to be learned. We propose to use Recurrent Neural Networks to encode motor sequences into a compact representation, which is used to predict the consequence of motor sequences in term of sensory changes. We show that sensory prediction can successfully guide the compression of motor sequences into representations that are organized topologically in term of spatial displacement.

Designing agile locomotion for quadruped robots often requires extensive expertise and tedious manual tuning. In this paper, we present a system to automate this process by leveraging deep reinforcement learning techniques. Our system can learn quadruped locomotion from scratch using simple reward signals. In addition, users can provide an open loop reference to guide the learning process when more control over the learned gait is needed. The control policies are learned in a physics simulator and then deployed on real robots. In robotics, policies trained in simulation often do not transfer to the real world. We narrow this reality gap by improving the physics simulator and learning robust policies. We improve the simulation using system identification, developing an accurate actuator model and simulating latency. We learn robust controllers by randomizing the physical environments, adding perturbations and designing a compact observation space. We evaluate our system on two agile locomotion gaits: trotting and galloping. After learning in simulation, a quadruped robot can successfully perform both gaits in the real world.

The sci-fi inspired concern that artificial intelligence will one day rule the world is (mostly) unfounded, but it certainly could have a huge impact on drug discovery. Traditionally, pharma companies have been skeptical about the promise of artificial intelligence (AI). But with its potential to bring powerful new tools to the often slow and expensive drug discovery process – and its ability to predict which drugs are most likely to successfully run the clinical trial gauntlet, pharma companies are waking up to the fact that it really could be the future. In 2017, a collaboration began between Insilico Medicine, an AI company specializing in deep learning for drug discovery, and Juvenescence – a company focused on investing in treatments for age-related diseases and longevity. To find out if AI techniques could enhance drug discovery in the tricky area of age-related diseases, including dementia, diabetes, and cancer, as well as the aging process itself.

This is a talk by Ilya Sutskever for course 6.S099: Artificial General Intelligence. He is the Co-Founder of OpenAI. This class is free and open to everyone. Our goal is to take an engineering approach to exploring possible paths toward building human-level intelligence for a better world.

Artificial intelligence startup Neurala Inc. is claiming a major breakthrough with its deep learning platform, saying it has reduced the time it takes to train a deep neural network from 15 hours to just 20 seconds. Neurala claims to differentiate itself from other AI software makers because its platform learns by mimicking the human brain, integrating sight, sound and other senses into one system in a rough emulation of how the mind works. The startup added that its deep learning software further excels because it doesn't rely on servers running in the cloud to train its systems, therefore making it suitable for a new generation of smart cars, children's toys and industrial machines that perform computations at the edge of the network. Now, the company said, its Lifelong Deep Neural Network technology is better than ever, slashing learning times to mere seconds and also providing the ability for neural networks to acquire new knowledge without forgetting the previous information it learned – something it claims wasn't possible before. "It takes a very long time to train a traditional DNN on a dataset, and once that happens, it must be completely retrained if even a single piece of new information is added," said Anatoli Gorchetchnikov, Neurala's chief technology officer.

We will start with a very simple baseline. We will represent the headline by averaging the headline words in their Word2Vec representation. As previously mentioned, Word2Vec is a machine-learning method for representing words as vectors. The Word2Vec model is trained by predicting words close to the target word with a shallow neural network. You can read more about how the algorithm works here.