Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot arm in simulation. Curiosity-driven exploration using the prediction error of a learned dynamics model as an intrinsic reward has been shown to be effective for exploring a number of sparse-reward environments. We present a method that combines hindsight with curiosity-driven exploration and curriculum learning in order to solve the challenging sparse-reward block stacking task. We are the first to stack more than two blocks using only sparse reward without human demonstrations.

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic cumbersome teacher model's output to get improved generalization. However, related methods mainly focus on simple task of classification while do not consider complex tasks like object detection. We show applying the vanilla knowledge distillation to detection model gets minor gain. To address the challenge of distilling knowledge in detection model, we propose a fine-grained feature imitation method exploiting the cross-location discrepancy of feature response. Our intuition is that detectors care more about local near object regions. Thus the discrepancy of feature response on the near object anchor locations reveals important information of how teacher model tends to generalize. We design a novel mechanism to estimate those locations and let student model imitate the teacher on them to get enhanced performance. We first validate the idea on a developed lightweight toy detector which carries simplest notion of current state-of-the-art anchor based detection models on challenging KITTI dataset, our method generates up to 15% boost of mAP for the student model compared to the non-imitated counterpart. We then extensively evaluate the method with Faster R-CNN model under various scenarios with common object detection benchmark of Pascal VOC and COCO, imitation alleviates up to 74% performance drop of student model compared to teacher. Codes released at https://github.com/twangnh/Distilling-Object-Detectors

After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for current Artificial Intelligence algorithms as persistent model retraining is necessary. Inspired by the Parallel Distributed Processing learning and the Complementary Learning Systems theories, we develop a computational model that is able to expand its previously learned concepts efficiently to new domains using a few labeled samples. We couple the new form of a concept to its past learned forms in an embedding space for effective continual learning. Doing so, a generative distribution is learned such that it is shared across the tasks in the embedding space and models the abstract concepts. This procedure enables the model to generate pseudo-data points to replay the past experience to tackle catastrophic forgetting.

We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of points that are disparate and high-magnitude when represented in a hallucinated gradient space, a strategy designed to incorporate both predictive uncertainty and sample diversity into every selected batch. Crucially, BADGE trades off between diversity and uncertainty without requiring any hand-tuned hyperparameters. We show that while other approaches sometimes succeed for particular batch sizes or architectures, BADGE consistently performs as well or better, making it a versatile option for practical active learning problems.

We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set of linguistic constructs but have limited training data. To address these challenges, we present the first system, to the best of our knowledge, that reasons over a wide range of semantic abstractions of the text, which are derived using off-the-shelf, general-purpose, pre-trained natural language modules such as semantic role labelers, coreference resolvers, and dependency parsers. Representing multiple abstractions as a family of graphs, we translate question answering (QA) into a search for an optimal subgraph that satisfies certain global and local properties. This formulation generalizes several prior structured QA systems. Our system, SEMANTICILP, demonstrates strong performance on two domains simultaneously. In particular, on a collection of challenging science QA datasets, it outperforms various state-of-the-art approaches, including neural models, broad coverage information retrieval, and specialized techniques using structured knowledge bases, by 2%-6%.

Now, in theory, it is possible to become a data scientist, without paying a dime. What we want to do in this article is to list out the best of the best options to learn what you need to know to become a data scientist. Many articles offer 4-5 courses under each heading. What I have done is to search through the Internet covering all free courses and choose the single best course for each topic. These courses have been carefully curated and offer the best possible option if you're learning for free.

In his session at 23rd International CloudEXPO, Raju Shreewastava, founder of Big Data Trunk, will provide a fun and simple way to introduce Machine Leaning to anyone and everyone. Together we will solve a machine learning problem and find an easy way to be able to do machine learning without even coding. He solved a machine learning problem and demonstrated an easy way to be able to do machine learning without even coding. Speaker Bio Raju Shreewastava is the founder of Big Data Trunk (www.BigDataTrunk.com), a Big Data Training and consulting firm with offices in the United States. He previously led the data warehouse/business intelligence and Big Data teams at Autodesk.

The rise of technology within the education sector over the last few decades has been astounding. This is certainly the case if we consider that teaching with technology has become pervasive in almost every classroom environment. Within today's classroom, for example, we find ourselves surrounded by devices such as smart boards, AV, computers, laptops, tablets and phones, to name but a few technologies which are now being integrated into teaching. We have also seen the rise of the virtual learning environment and blended learning, alongside a significant rise in online education. This has allowed distance learning to take new forms and shapes and to reach greater audiences around the world.

Machine learning is expanding its scope to get the title of the trendiest job market across the globe. Techno-experts and various establishments are investing billions into this fleshly coming up industry. As per statista the chief reason for the adoption of machine learning technology according to 33% of individuals is its use in business analysis. Offering a handful of opportunities, freshers of IT as well as experienced individuals are willing to know more about the different programming coding and language tool to establish themselves wholeheartedly in the machine learning software. Among all this, there are various non-programmers who don't possess to have any kind of knowledge about coding and yet desires to walk in the vicinity of machine language and remain functioning in the industry.

The rise of technology within the education sector over the last few decades has been astounding. This is certainly the case if we consider that teaching with technology has become pervasive in almost every classroom environment. Within today's classroom, for example, we find ourselves surrounded by devices such as smart boards, AV, computers, laptops, tablets and phones, to name but a few technologies which are now being integrated into teaching. We have also seen the rise of the virtual learning environment and blended learning, alongside a significant rise in online education. This has allowed distance learning to take new forms and shapes and to reach greater audiences around the world.