We present Multitask Soft Option Learning (MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational posteriors for each task, regularized by a shared prior. This allows fine-tuning of options for new tasks without forgetting their learned policies, leading to faster training without reducing the expressiveness of the hierarchical policy. Additionally, MSOL avoids several instabilities during training in a multitask setting and provides a natural way to not only learn intra-option policies, but also their terminations. We demonstrate empirically that MSOL significantly outperforms both hierarchical and flat transfer-learning baselines in challenging multi-task environments.

In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic motivation. Specifically, we designed intrinsic rewards generated from UL modules for driving the RL agent to focus on objects for a period of time and to learn good representations of objects for later object recognition task. We evaluate our proposed algorithm in both with and without extrinsic reward settings. Experiments with end-to-end training in simulated environments with applications to few-shot object recognition demonstrated the effectiveness of the proposed algorithm.

Video understanding is emerging as a new paradigm for studying human-like AI. Question-and-Answering (Q&A) is used as a general benchmark to measure the level of intelligence for video understanding. While several previous studies have suggested datasets for video Q&A tasks, they did not really incorporate story-level understanding, resulting in highly-biased and lack of variance in degree of question difficulty. In this paper, we propose a hierarchical method for building Q&A datasets, i.e. hierarchical difficulty levels. We introduce three criteria for video story understanding, i.e. memory capacity, logical complexity, and DIKW (Data-Information-Knowledge-Wisdom) pyramid. We discuss how three-dimensional map constructed from these criteria can be used as a metric for evaluating the levels of intelligence relating to video story understanding.

The field of geometric automated theorem provers has a long and rich history, from the early AI approaches of the 1960s, synthetic provers, to today algebraic and synthetic provers. The geometry automated deduction area differs from other areas by the strong connection between the axiomatic theories and its standard models. In many cases the geometric constructions are used to establish the theorems' statements, geometric constructions are, in some provers, used to conduct the proof, used as counter-examples to close some branches of the automatic proof. Synthetic geometry proofs are done using geometric properties, proofs that can have a visual counterpart in the supporting geometric construction. With the growing use of geometry automatic deduction tools as applications in other areas, e.g. in education, the need to evaluate them, using different criteria, is felt. Establishing a ranking among geometric automated theorem provers will be useful for the improvement of the current methods/implementations. Improvements could concern wider scope, better efficiency, proof readability and proof reliability. To achieve the goal of being able to compare geometric automated theorem provers a common test bench is needed: a common language to describe the geometric problems; a comprehensive repository of geometric problems and a set of quality measures.

Abstract: "In this talk I will cover some of the recent work out of the Socially Intelligent Machines Lab at UT Austin (http://sim.ece.utexas.edu/research.html). The vision of our research is to enable robots to function in dynamic human environments by allowing them to flexibly adapt their skill set via learning interactions with end-users. We explore the ways in which Machine Learning agents can exploit principles of human social learning, and breakdown assumptions about what "data" will be like, when the source of that data is an average human teacher. I will cover our work on interactive reinforcement learning algorithms that model the attention of the teacher; coupling learning from demonstration with simulation to make the best use of valuable interactions with people; and algorithms for re-using previously learned tasks in new contexts with the help of a teacher's hints and corrections. In the latter part of the talk, I will put on my other hat, as co-founder and CEO of Diligent Robotics (http://diligentrobots.com/about) to tell you about how we are translating our research on adapting to human environments into a commercial product. Our first product, Moxi, is a robot assistant that works alongside and supports clinical care teams in hospitals. Moxi was launched into beta trials late last year, and has been deployed in four hospitals across Texas to date."

Statistical approaches to processing natural language text have become dominant during the recent years. This foundational text is the first comprehensive introduction to statistical natural language processing (NLP) to appear. This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. This course explains why predictive analytics projects are ultimately classification problems, and how data scientists can choose the right strategy for their projects. This book covers the field of machine learning, which is the study of algorithms that allow computer programs to automatically improve through experience.

A proprietary machine learning algorithm is behind Pluralsight's ability to accurately assess technology skills. Organizations are increasingly using technology to gain strategic competitive advantages. A problem for employers is an overall lack of technology-based skills across the workforce. Pluralsight (PS), provider of a cloud-based technology learning platform, is one vendor leading the disruption in corporate training. Pluralsight management has referred to the company as "the supply chain" of technology skills.

This paper presents a educational workshop in Scratch that is proposed for the active participation of undergraduate students in contexts of Artificial Intelligence. The main objective of the activity is to demystify the complexity of Artificial Intelligence and its algorithms. For this purpose, students must realize simple exercises of clustering and two neural networks, in Scratch. The detailed methodology to get that is presented in the article.

To master English as a native speaker, the average adult has to learn almost as much information as the contents of a full floppy disk, experts estimate. That amount of information translates to 12.5 million bits or roughly 1.5 megabytes (mb), while the iconic storage device holds 1.44mb of information. The data is mostly in the form of word definitions rather than complex structures like grammar. This is the first time that researchers have tried try to work out the amount of information our brains need to store in order to master a single language. Researchers from the University of Rochester in New York analysed different aspects of language learning and found the average learner acquires nearly 2,000 bits of information about how language works daily.

As much as we'd like to, nobody knows exactly what the future holds. However, several individuals have put their minds, time, and effort toward figuring out what the future of marketplaces, industry, and work will look like to the greatest possible degree of accuracy. For those who are looking to figure out which industries are most ripe for disruption, which are dinosaurs, and how the future of work applies in your own life, these forward-looking influencers are must-follows. But don't just stop at their Twitter pages, as these influencers have personal websites, TED Talks, and more that are well worth checking out. This influencer has racked up several job titles on his way to becoming one of the most popular voicers in the future of work sphere.