Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator. However, standard imitation learning methods assume that the agent receives examples of observation-action tuples that could be provided, for instance, to a supervised learning algorithm. This stands in contrast to how humans and animals imitate: we observe another person performing some behavior and then figure out which actions will realize that behavior, compensating for changes in viewpoint, surroundings, object positions and types, and other factors. We term this kind of imitation learning "imitation-from-observation," and propose an imitation learning method based on video prediction with context translation and deep reinforcement learning. This lifts the assumption in imitation learning that the demonstration should consist of observations in the same environment configuration, and enables a variety of interesting applications, including learning robotic skills that involve tool use simply by observing videos of human tool use. Our experimental results show the effectiveness of our approach in learning a wide range of real-world robotic tasks modeled after common household chores from videos of a human demonstrator, including sweeping, ladling almonds, pushing objects as well as a number of tasks in simulation.

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.

NEW DELHI: The government should drive cross-border collaboration on artificial intelligence research with countries like Japan, UK, Germany, Singapore, Israel and China to develop solutions that tackle social and economic challenges, a report said today. The Ministry of External Affairs and Department of Science and Technology (DST) may take the lead in developing such relationships, suggested the Assocham-PwC joint study. It observed that forming cooperative relationships with some of the front-runners such as Japan, the UK, Germany, Singapore, Israel and China to develop solutions that tackle social and economic challenges can aid and accelerate strategy formulation in artificial intelligence, machine learning and other new-age technologies in India. "Exchanging best practices and learning from prior initiatives is one way of strengthening cooperation," noted the study. The study also suggested that policy planning in artificial intelligence (AI) must be aimed at creating an ecosystem that is supportive of research, innovation and commercialisation of applications.

"The public sector, with its various schemes (Digital India, Make in India, Skill India), could identify areas where specific applications of AI and robotics can be utilised to increase reach, effectiveness and efficiency, thus giving direction to existing innovation across different fields," the study said. Indian government departments should take the lead in developing cross-border collaborations with countries leading in Artificial Intelligence (AI) research, industry chamber Assocham said on Sunday. The departments like the External Affairs Ministry (MEA) and the Department of Science and Technology (DST), should drive cooperative relationships with frontrunners like Japan, the UK, Germany, Singapore, Israel and China to develop solutions for social and economic challenges and accelerate strategy formulation in AI, machine learning (ML) and other new technologies, Assocham said citing its joint study with British advisory multinational PricewaterhouseCoopers (PwC). "Exchanging best practices and learnings from prior initiatives is one way of strengthening cooperation," the study titled "Advance artificial intelligence for growth: Leveraging AI and robotics for India's economic transformation" said.A It also suggested that policy planning in AI must be aimed at creating an ecosystem that is supportive of research, innovation and commercialisation of applications. "The public sector, with its various schemes (Digital India, Make in India, Skill India), could identify areas where specific applications of AI and robotics can be utilised to increase reach, effectiveness and efficiency, thus giving direction to existing innovation across different fields," the study said.

This course is focused on the question: How do we do matrix computations with acceptable speed and acceptable accuracy? This course was taught in the University of San Francisco's Masters of Science in Analytics program, summer 2017 (for graduate students studying to become data scientists). The course is taught in Python with Jupyter Notebooks, using libraries such as Scikit-Learn and Numpy for most lessons, as well as Numba (a library that compiles Python to C for faster performance) and PyTorch (an alternative to Numpy for the GPU) in a few lessons. Accompanying the notebooks is a playlist of lecture videos, available on YouTube. If you are ever confused by a lecture or it goes too quickly, check out the beginning of the next video, where I review concepts from the previous lecture, often explaining things from a new perspective or with different illustrations, and answer questions.

Feature engineering is one of the most important but most tedious tasks in data science. This work studies automation of feature learning from relational database. We first prove theoretically that finding the optimal features from relational data for predictive tasks is NP-hard. We propose an efficient rule-based approach based on heuristics and a deep neural network to automatically learn appropriate features from relational data. We benchmark our approaches in ensembles in past Kaggle competitions. Our new approach wins late medals and beats the state-of-the-art solutions with significant margins. To the best of our knowledge, this is the first time an automated data science system could win medals in Kaggle competitions with complex relational database.

Modeling agent behavior is central to understanding the emergence of complex phenomena in multiagent systems. Prior work in agent modeling has largely been task-specific and driven by hand-engineering domain-specific prior knowledge. We propose a general learning framework for modeling agent behavior in any multiagent system using only a handful of interaction data. Our framework casts agent modeling as a representation learning problem. Consequently, we construct a novel objective inspired by imitation learning and agent identification and design an algorithm for unsupervised learning of representations of agent policies. We demonstrate empirically the utility of the proposed framework in (i) a challenging high-dimensional competitive environment for continuous control and (ii) a cooperative environment for communication, on supervised predictive tasks, unsupervised clustering, and policy optimization using deep reinforcement learning.

Presenting Fritz Schiltz our youngest speaker of #disummit – he will talk about using #machinelearning to improve the ranking system of schools. Fritz is an applied econometrician at the University of Leuven where he applies advanced analytics to evaluate policies, mainly in education. He has worked on reports for the European Union, the Ministry of Education and Syntra. Halfway his PhD in Economics he shifted his interests towards machine learning methods. His presentation is the result from joint work with the Bank of Italy and illustrates how machine learning or AI methods can be used to improve school rankings using an Italian dataset.

Artificial intelligence could be heading to Australian classrooms -- and in schools overseas, it's already there. In Bahia, Brazil, 15-year-old students David and Roama from Colegio Perfil often start their school day at home, or on the bus. They pick up their phones, log into the education app Geekie Lab, and begin their classes from wherever they are. "You can access it everywhere, as long as you have your phone with you," David said. Students from Colegio Perfil in Bahia use phones or computers to access the Geekie app.

In my previous blog, I wrote that employees these days are hungry for a more dynamic, collaborative workplace experience, one that provides pervasive access to productivity tools so they can work wherever they choose. Create a Great Employee Experience.) Next, we need to consider that work activities flow across not only different workspaces, but also different systems and devices. One minute you need some private office space and a bit of peace and quiet to hammer out a spreadsheet on a PC. Next minute you're in a conference room using your laptop to practice delivery of a presentation and getting feedback from a group of colleagues.