Many modern machine learning approaches require vast amounts of training data to learn new concepts; conversely, human learning often requires few examples--sometimes only one--from which the learner can abstract structural concepts. We present a novel approach to introducing new spatial structures to an AI agent, combining deep learning over qualitative spatial relations with various heuristic search algorithms. The agent extracts spatial relations from a sparse set of noisy examples of block-based structures, and trains convolutional and sequential models of those relation sets. To create novel examples of similar structures, the agent begins placing blocks on a virtual table, uses a CNN to predict the most similar complete example structure after each placement, an LSTM to predict the most likely set of remaining moves needed to complete it, and recommends one using heuristic search. We verify that the agent learned the concept by observing its virtual block-building activities, wherein it ranks each potential subsequent action toward building its learned concept. We empirically assess this approach with human participants' ratings of the block structures. Initial results and qualitative evaluations of structures generated by the trained agent show where it has generalized concepts from the training data, which heuristics perform best within the search space, and how we might improve learning and execution.

Today, I'm excited to share that, for the first time, the same machine learning courses used to train engineers at Amazon are now available to all developers through AWS. We've been using machine learning across Amazon for more than 20 years. With thousands of engineers focused on machine learning across the company, there are very few Amazon retail pages, products, fulfillment technologies, stores which haven't been improved through the use of machine learning in one way or another. Many AWS customers share this enthusiasm, and our mission has been to take machine learning from something which had previously been only available to the largest, most well-funded technology companies, and put it in the hands of every developer. Thanks to services such as Amazon SageMaker, Amazon Rekognition, Amazon Comprehend, Amazon Transcribe, Amazon Polly, Amazon Translate, and Amazon Lex, tens of thousands of developers are already on their way to building more intelligent applications through machine learning.

Recent years have witnessed the rising popularity of Natural Language Processing (NLP) and related fields such as Artificial Intelligence (AI) and Machine Learning (ML). Many online courses and resources are available even for those without a strong background in the field. Often the student is curious about a specific topic but does not quite know where to begin studying. To answer the question of "what should one learn first," we apply an embedding-based method to learn prerequisite relations for course concepts in the domain of NLP. We introduce LectureBank, a dataset containing 1,352 English lecture files collected from university courses which are each classified according to an existing taxonomy as well as 208 manually-labeled prerequisite relation topics, which is publicly available. The dataset will be useful for educational purposes such as lecture preparation and organization as well as applications such as reading list generation. Additionally, we experiment with neural graph-based networks and non-neural classifiers to learn these prerequisite relations from our dataset.

Looking to get into programming, but don't know where to start? Maybe you've heard of some of the most popular programming languages, but you're unsure of which one is best to learn first? Python is hands-down the best language to start with if you want to learn how to program. There's a reason why 70% of introductory programming courses teach Python at US universities according to Tech Republic. Python is one of the most popular, beginner friendly languages, and it's also the first language I learned back in 2014.

Much the way that a master key can unlock every door in a building, these "DeepMasterPrints" use artificial intelligence to match a large number of prints stored in fingerprint databases and could thus theoretically unlock a large number of devices. The research team was headed by NYU Tandon Associate Professor of Computer Science and Engineering Julian Togelius and doctoral student Philip Bontrager, the lead author of the paper, who presented it at the IEEE International Conference of Biometrics: Theory, Applications and Systems, where it won the Best Paper Award. The work builds on earlier research led by Nasir Memon, professor of computer science and engineering and associate dean for online learning at NYU Tandon. Memon, who coined the term "MasterPrint," described how fingerprint-based systems use partial fingerprints, rather than full ones, to confirm identity. Devices typically allow users to enroll several different finger images, and a match for any saved partial print is enough to confirm identity.

If you remember anything from Calculus (not a trivial feat), it might have something to do with optimization. Finding the best numerical solution to a given problem is an important part of many branches in mathematics, and Machine Learning is no exception. Optimizers, combined with their cousin the Loss Function, are the key pieces that enable Machine Learning to work for your data. This post will walk you through the optimization process in Machine Learning, how loss functions fit into the equation (no pun intended), and some popular approaches. We'll also include some resources for further reading and experimentation.

Born in the city of Nagoya in 1970, he spent his teenage years devouring popular anime series of the time, including "Mobile Suit Zeta Gundam," the sequel in the well-known Gundam franchise that first aired in 1985, and "Dirty Pair," a sci-fi adventure featuring a sexy female duo working as "trouble consultants." This was the heyday of the VHS cassette, and Goto would spend his allowance renting anime tapes, many of which were made specifically for release on home video format to meet the period's surging demand for anime content. It wasn't a hobby he could openly share with his classmates, however. This was years before the otaku image underwent a makeover of sorts, thanks to the popularization of the fan culture and its global acceptance as a source of soft power. "Otaku of our generation were typically way down in the'school caste' system, and girls tended to look at us with disdain," he says, referring to the invisible hierarchy in the classroom determined by different status symbols.

This beginner-friendly Python course will take you from zero to programming in Python in a matter of hours.

Recurrent neural networks (RNNs) such as long short-term memory and gated recurrent units are pivotal building blocks across a broad spectrum of sequence modeling problems. This paper proposes a recurrently controlled recurrent network (RCRN) for expressive and powerful sequence encoding. More concretely, the key idea behind our approach is to learn the recurrent gating functions using recurrent networks. Our architecture is split into two components - a controller cell and a listener cell whereby the recurrent controller actively influences the compositionality of the listener cell. We conduct extensive experiments on a myriad of tasks in the NLP domain such as sentiment analysis (SST, IMDb, Amazon reviews, etc.), question classification (TREC), entailment classification (SNLI, SciTail), answer selection (WikiQA, TrecQA) and reading comprehension (NarrativeQA). Across all 26 datasets, our results demonstrate that RCRN not only consistently outperforms BiLSTMs but also stacked BiLSTMs, suggesting that our controller architecture might be a suitable replacement for the widely adopted stacked architecture.

An important field in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent. When gradient-based methods are used, models are kept small or rely on finite difference approximations for the Jacobian. This method quickly grows expensive with increasing numbers of parameters, such as found in deep learning. We propose the implementation of a modern physics engine, which can differentiate control parameters. This engine is implemented for both CPU and GPU. Firstly, this paper shows how such an engine speeds up the optimization process, even for small problems. Furthermore, it explains why this is an alternative approach to deep Q-learning, for using deep learning in robotics. Finally, we argue that this is a big step for deep learning in robotics, as it opens up new possibilities to optimize robots, both in hardware and software.