Indian Institute of Science's Machine Learning Special Interest Group: Touted as one of the best research groups in India, especially the one with a beautiful campus, IISc's MLSIG features several talented students and faculty members engaged in cutting-edge research on a variety of aspects of ML and related fields. These works range from theoretical foundations to new algorithms as well as other exciting applications. IISc MLSIG has a great roster of events that covers topics such as deep learning with GPUs, data mining (models, algorithms and applications), text analysis, knowledge representation and reasoning with DNN. MLSIG is also doing cutting-edge research that is published in top journals and conferences. Some of the research topics are ML in text mining, ML in computer vision, graphical models, clustering, support vector machines and kernel-based learning methods.

Pathfinding is a very popular area in computer game development. While two-dimensional (2D) pathfinding is widely applied in most of the popular game engines, little implementation of real three-dimensional (3D) pathfinding can be found. This research presents a dynamic search space optimization algorithm which can be applied to tessellate 3D search space unevenly, significantly reducing the total number of resulting nodes. The algorithm can be used with popular pathfinding algorithms in 3D game engines. Furthermore, a simplified standalone 3D pathfinding algorithm is proposed in this paper. The proposed algorithm relies on ray-casting or line vision to generate a feasible path during runtime without requiring division of the search space into a 3D grid. Both of the proposed algorithms are simulated on Unreal Engine to show innerworkings and resultant path comparison with A*. The advantages and shortcomings of the proposed algorithms are also discussed along with future directions.

Incredibly, the system learned to dominate the classic 3D puzzle in just 44 hours and without any human intervention. "A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision," write the authors of the new paper, published online at the arXiv preprint server. Indeed, if we're ever going to achieve a general, human-like machine intelligence, we'll have to develop systems that can learn and then apply those learnings to real-world applications. Recent breakthroughs in machine learning have produced systems that, without any prior knowledge, have learned to master games like chess and Go. But these approaches haven't translated very well to the Rubik's Cube.

OK, let's break this down. The Rubik's Cube is pretty difficult, right? But you'd imagine it might be pretty easy for an artificial intelligence to break down and solve consistently, right? Creating an algorithm that can solve the Rubik's Cube is relatively simple -- the kind of algorithms that allow AI to beat humans at chess or Go or even DOTA 2! But creating a machine that can solve the Rubik's Cube without algorithms hand-crafted by human beings? Stephen McAleer and his colleagues at the University of California think they have solved the problem, with a process called "autodidactic iteration". Autodidactic iteration: McAleer and his team call it a "novel reinforcement learning algorithm that is able to teach itself how to solve the Rubik's Cube with no human assistance."

Deep-learning machines have figured out how to master games like chess or Mortal Kombat. Now, computer scientists at the University of California, Irvine taken things to the third dimension by creating an algorithm that can figure out how to solve a Rubik's Cube, a surprisingly difficult change. "Our algorithm is able to solve 100 percent of randomly scrambled cubes while achieving a median solve length of 30 moves - less than or equal to solvers that employ human domain knowledge," say the scientists in the abstract to their paper, up on Arvix. The algorithm, called DeepCube, uses what's known as "autodidactic iteration," a form of machine learning developed by the authors of the paper. The big challenge of autodidactic iteration was to allow machines to find their own rewards in solving a puzzle, a goal they can reach.

The Rubik's Cube is a three-dimensional puzzle developed in 1974 by the Hungarian inventor Erno Rubik, the object being to align all squares of the same color on the same face of the cube. It became an international best-selling toy and sold over 350 million units. The puzzle has also attracted considerable interest from computer scientists and mathematicians. One question that has intrigued them is the smallest number of moves needed to solve it from any position. The answer, proved in 2014, turns out to be 26.

This survey discusses how recent developments in multimodal processing facilitate conceptual grounding of language. We categorize the information flow in multimodal processing with respect to cognitive models of human information processing and analyze different methods for combining multimodal representations. Based on this methodological inventory, we discuss the benefit of multimodal grounding for a variety of language processing tasks and the challenges that arise. We particularly focus on multimodal grounding of verbs which play a crucial role for the compositional power of language.

The Rubik's Cube is a three-dimensional puzzle developed in 1974 by the Hungarian inventor Erno Rubik, the object being to align all squares of the same color on the same face of the cube. It became an international best-selling toy and sold over 350 million units. The puzzle has also attracted considerable interest from computer scientists and mathematicians. One question that has intrigued them is the smallest number of moves needed to solve it from any position. The answer, proved in 2014, turns out to be 26.

Deep-learning machines have figured out how to master games like chess or Mortal Kombat. Now, computer scientists at the University of California, Irvine taken things to the third dimension by creating an algorithm that can figure out how to solve a Rubik's Cube, a surprisingly difficult change. "Our algorithm is able to solve 100 percent of randomly scrambled cubes while achieving a median solve length of 30 moves -- less than or equal to solvers that employ human domain knowledge," say the scientists in the abstract to their paper, up on Arvix. The algorithm, called DeepCube, uses what's known as "autodidactic iteration," a form of machine learning developed by the authors of the paper. The big challenge of autodidactic iteration was to allow machines to find their own rewards in solving a puzzle, a goal they can reach.

Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do so, we train a speedup classifier that learns to mimic a black-box classifier under the learning-to-search approach. As the structured classifier predicts more examples, the speedup classifier will operate as a learned heuristic to guide search to favorable regions of the output space. We present a mistake bound for the speedup classifier and identify inference situations where it can independently make correct judgments without input features. We evaluate our method on the task of entity and relation extraction and show that the speedup classifier outperforms even greedy search in terms of speed without loss of accuracy.