Abstract--In this paper, learning of tree-structured Gaussian graphical models from distributed data is addressed. In our model, samples are stored in a set of distributed machines where each machine has access to only a subset of features. A central machine is then responsible for learning the structure based on received messages from the other nodes. We present a set of communication efficient strategies, which are theoretically proved to convey sufficient information for reliable learning of the structure. In particular, our analyses show that even if each machine sends only the signs of its local data samples to the central node, the tree structure can still be recovered with high accuracy. Our simulation results on both synthetic and real-world datasets show that our strategies achieve a desired accuracy in inferring the underlying structure, while spending a small budget on communication. In many situations, it is impossible to transfer the distributed data completely to a central machine due to communication constraints. Designing communication-efficient learning algorithms is desired to transfer enough information from repositories to the central machine and to reliably infer the learning model. Many learning algorithms can be modified to run distributively at several machines to perform a learning task.

Automatic spelling and grammatical correction systems are one of the most widely used tools within natural language applications. In this thesis, we assume the task of error correction as a type of monolingual machine translation where the source sentence is potentially erroneous and the target sentence should be the corrected form of the input. Our main focus in this project is building neural network models for the task of error correction. In particular, we investigate sequence-to-sequence and attention-based models which have recently shown a higher performance than the state-of-the-art of many language processing problems. We demonstrate that neural machine translation models can be successfully applied to the task of error correction. While the experiments of this research are performed on an Arabic corpus, our methods in this thesis can be easily applied to any language.

Over the past few years, adversarial training has become an extremely active research topic and has been successfully applied to various Artificial Intelligence (AI) domains. As a potentially crucial technique for the development of the next generation of emotional AI systems, we herein provide a comprehensive overview of the application of adversarial training to affective computing and sentiment analysis. Various representative adversarial training algorithms are explained and discussed accordingly, aimed at tackling diverse challenges associated with emotional AI systems. Further, we highlight a range of potential future research directions. We expect that this overview will help facilitate the development of adversarial training for affective computing and sentiment analysis in both the academic and industrial communities.

In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms will estimate the value function more accurately and find a better policy. When the state space is large or continuous \emph{Gradient-based Temporal Difference(GTD)} policy evaluation algorithms with linear function approximation are widely used. Considering that the collection of the evaluation data is both time and reward consuming, a clear understanding of the finite sample performance of the policy evaluation algorithms is very important to reinforcement learning. Under the assumption that data are i.i.d. generated, previous work provided the finite sample analysis of the GTD algorithms with constant step size by converting them into convex-concave saddle point problems. However, it is well-known that, the data are generated from Markov processes rather than i.i.d. in RL problems.. In this paper, in the realistic Markov setting, we derive the finite sample bounds for the general convex-concave saddle point problems, and hence for the GTD algorithms. We have the following discussions based on our bounds. (1) With variants of step size, GTD algorithms converge. (2) The convergence rate is determined by the step size, with the mixing time of the Markov process as the coefficient. The faster the Markov processes mix, the faster the convergence. (3) We explain that the experience replay trick is effective by improving the mixing property of the Markov process. To the best of our knowledge, our analysis is the first to provide finite sample bounds for the GTD algorithms in Markov setting.

Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample complexity of the new tasks. Considering that data collection in RL is both more time and cost consuming and Q-learning converges slowly comparing to supervised learning, different kinds of transfer RL algorithms are designed. However, most of them are heuristic with no theoretical guarantee of the convergence rate. Therefore, it is important for us to clearly understand when and how will transfer learning help RL method and provide the theoretical guarantee for the improvement of the sample complexity. In this paper, we propose to transfer the Q-function learned in the source task to the target of the Q-learning in the new task when certain safe conditions are satisfied. We call this new transfer Q-learning method target transfer Q-Learning. The safe conditions are necessary to avoid the harm to the new tasks and thus ensure the convergence of the algorithm. We study the convergence rate of the target transfer Q-learning. We prove that if the two tasks are similar with respect to the MDPs, the optimal Q-functions in the source and new RL tasks are similar which means the error of the transferred target Q-function in new MDP is small. Also, the convergence rate analysis shows that the target transfer Q-Learning will converge faster than Q-learning if the error of the transferred target Q-function is smaller than the current Q-function in the new task. Based on our theoretical results, we design the safe condition as the Bellman error of the transferred target Q-function is less than the current Q-function. Our experiments are consistent with our theoretical founding and verified the effectiveness of our proposed target transfer Q-learning method.

We propose a video story question-answering (QA) architecture, Multimodal Dual Attention Memory (MDAM). The key idea is to use a dual attention mechanism with late fusion. MDAM uses self-attention to learn the latent concepts in scene frames and captions. Given a question, MDAM uses the second attention over these latent concepts. Multimodal fusion is performed after the dual attention processes (late fusion). Using this processing pipeline, MDAM learns to infer a high-level vision-language joint representation from an abstraction of the full video content. We evaluate MDAM on PororoQA and MovieQA datasets which have large-scale QA annotations on cartoon videos and movies, respectively. For both datasets, MDAM achieves new state-of-the-art results with significant margins compared to the runner-up models. We confirm the best performance of the dual attention mechanism combined with late fusion by ablation studies. We also perform qualitative analysis by visualizing the inference mechanisms of MDAM.

According to the report, global GDP could be up to 14 percent higher in 2030 as a result of AI. This is the equivalent of an additional USD 15.7 trillion – making it the biggest commercial opportunity in today's fast changing economy. Of this, USD 6.6 trillion is likely to come from increased productivity and USD 9.1 trillion from consumption side effects, the report shows. Accordingly, growth will be driven by three factors: productivity gains from businesses automating processes (including use of robots and autonomous vehicles); productivity gains from businesses augmenting their existing labour force with AI technologies (assisted and augmented intelligence) and increased consumer demand resulting from the availability of personalised and/or higher-quality AI-enhanced products and services. Over the past decade, almost all aspects of how we work and how we live – from retail to manufacturing to healthcare – have become increasingly digitised, the report notes.

The terms'data science' and'analytics' have had a great surge in usage for a long time now. Data has become the driving force of all established companies these days. In this ever-evolving sector of technology, success and failure stories are found daily. But only a few of them are as inspiring as the story of Ankush Bhandari, a tiffin service provider who became a data scientist. Ankush Bhandari completed his Master in Economics at Fergusson College, Pune, and started his entrepreneurial venture – Kaivalya Foods – as a tiffin service provider.

Could you perceive the touch of an ant's antenna on your fingertip? This new tactile sensor can, and its inventors report that it could one day be integrated into prostheses to give wearers a superhuman sense of touch. The sensor converts pressure from touch to electric signals that, theoretically, could be perceived by the brain. Researchers at the Chinese Academy of Sciences in Ningbo, Zhenhai, described their invention yesterday in the journal Science Robotics. There have been a lot of touch sensors described in the literature, but this one's sensitivity is off the charts.

When the original Echo Show debuted last year, plenty of people (including us) made fun of its chunky and bulky design. Well, Amazon must've taken those comments to heart, because the new Echo Show is decidedly much better looking. While the older Echo Show might've reminded us of mall kiosks, the newer Show looks a bit more like a smaller, cuter TV. I tried it out briefly, following the Amazon announcement earlier today, and the first thing I noticed is that it's much more minimalist in design, with a beautiful 10-inch HD display dominating the front. It even takes up less counter space than the Google-powered 10-inch Lenovo Smart Display.