It is challenging to train deep neural networks robustly with noisy labels, as the capacity of deep neural networks is so high that they can totally over-fit on these noisy labels. In this paper, motivated by the memorization effects of deep networks, which shows networks fit clean instances first and then noisy ones, we present a new paradigm called "\textit{Co-teaching}" combating with noisy labels. We train two networks simultaneously. First, in each mini-batch data, each network filters noisy instances based on memorization effects. Then, it teaches the remained instances to its peer network for updating the parameters. Empirical results on benchmark datasets demonstrate that, the robustness of deep learning models trained by Co-teaching approach is much superior than that of state-of-the-art methods.

Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning. In this paper, we propose a simple but effective neural language grounding module for embodied agents that can be trained end to end from scratch taking raw pixels, unstructured linguistic commands, and sparse rewards as the inputs. We model the language grounding process as a language-guided transformation of visual features, where latent sentence embeddings are used as the transformation matrices. In several language-directed navigation tasks that feature challenging partial observation and require simple reasoning, our module significantly outperforms the state of the arts. We also release XWORLD 3D, an easy-to-customize 3D environment that can potentially be modified to evaluate a variety of embodied agents.

A fundamental challenge in imperfect-information games is that states do not have well-defined values. As a result, depth-limited search algorithms used in single-agent settings and perfect-information games do not apply. This paper introduces a principled way to conduct depth-limited solving in imperfect-information games by allowing the opponent to choose among a number of strategies for the remainder of the game at the depth limit. Each one of these strategies results in a different set of values for leaf nodes. This forces an agent to be robust to the different strategies an opponent may employ. We demonstrate the effectiveness of this approach by building a master-level heads-up no-limit Texas hold'em poker AI that defeats two prior top agents using only a 4-core CPU and 16 GB of memory. Developing such a powerful agent would have previously required a supercomputer.

Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only while training, but also when deployed at scales ranging from data centers all the way down to embedded devices. As such, increasing consideration is being made to maximize the computational efficiency given limited hardware and energy resources and, as a result, inferencing with reduced precision has emerged as a viable alternative to the IEEE 754 Standard for Floating-Point Arithmetic. We propose a quantization scheme that allows inferencing to be carried out using arithmetic that is fundamentally more efficient when compared to even half-precision floating-point. Our quantization procedure is significant in that we determine our quantization scheme parameters by calibrating against its reference floating-point model using a single inference batch rather than (re)training and achieve end-to-end post quantization accuracies comparable to the reference model.

As it requires a huge number of parameters when exposed to high dimensional inputs in video detection and classification, there is a grand challenge to develop a compact yet accurate video comprehension at terminal devices. Current works focus on optimizations of video detection and classification in a separated fashion. In this paper, we introduce a video comprehension (object detection and action recognition) system for terminal devices, namely DEEPEYE. Based on You Only Look Once (YOLO), we have developed an 8-bit quantization method when training YOLO; and also developed a tensorized-compression method of Recurrent Neural Network (RNN) composed of features extracted from YOLO. The developed quantization and tensorization can significantly compress the original network model yet with maintained accuracy. Using the challenging video datasets: MOMENTS and UCF11 as benchmarks, the results show that the proposed DEEPEYE achieves 3.994x model compression rate with only 0.47% mAP decreased; and 15,047x parameter reduction and 2.87x speed-up with 16.58% accuracy improvement.

About this course: This course will teach you how to build models for natural language, audio, and other sequence data. Thanks to deep learning, sequence algorithms are working far better than just two years ago, and this is enabling numerous exciting applications in speech recognition, music synthesis, chatbots, machine translation, natural language understanding, and many others. You will: - Understand how to build and train Recurrent Neural Networks (RNNs), and commonly-used variants such as GRUs and LSTMs. This is the fifth and final course of the Deep Learning Specialization. You will have the opportunity to build a deep learning project with cutting-edge, industry-relevant content.

Artificial Intelligence is one of the hottest fields in computer science right now and has taken the world by storm as a major field of research and development. Python has surfaced as a dominant language in AI/ML programming because of its simplicity and flexibility, as well as its great support for open source libraries such as Scikit-learn, Keras, spaCy, and TensorFlow. If you're a Python developer who wants to take first steps in the world of artificial intelligent solutions using easy-to-follow projects, then go for this learning path. This comprehensive 2-in-1 course is designed to teach you the fundamentals of deep learning and use them to build intelligent systems. You will solve real-world problems such as face detection, handwriting recognition, and more.

This is the new book by Andrew Ng, still in progress. Andrew Yan-Tak Ng is a computer scientist and entrepreneur. He is one of the most influential minds in Artificial Intelligence and Deep Learning. Ng founded and led Google Brain and was a former VP & Chief Scientist at Baidu, building the company's Artificial Intelligence Group into several thousand people. He is an adjunct professor (formerly associate professor and Director of the AI Lab) at Stanford University.

Deep Learning is an algorithm which has no theoretical limitations of what it can learn; the more data you give and the more computational time you give, the better it is – Sir Geoffrey Hinton (Google). The true challenge to Artificial Intelligence is to prove and solve the tasks that are easy for human to perform but hard to describe formally. Problems that we solve intuitively, that feel automatic, like recognizing spoken words or faces in images. In deep learning this is the task we try to solve at AILabPage research. At the same time I also claim It is absolutely wrong to call Deep Learning as Machine Learning (in my opinion).

Figure Eight can help you train, test, and tune your machine learning models, but building a strategy for your AI infrastructure can be challenging –– especially for compute-intensive deep learning workloads. That's why I&O leaders must choose the right accelerators for devising effective deep learning compute infrastructure strategies. Download the report Find the Right Accelerator for your Deep Learning Needs to learn how I&O leaders must deliver effective machine learning infrastructures that effectively balance performance, cost, and functionality while minimizing complexity.