Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches. In this paper, we build a framework in which we can fairly compare new vocoding and acoustic modeling techniques with conventional approaches by means of a large scale crowdsourced evaluation. Results on acoustic models showed that generative adversarial networks and an autoregressive (AR) model performed better than a normal recurrent network and the AR model performed best. Evaluation on vocoders by using the same AR acoustic model demonstrated that a Wavenet vocoder outperformed classical source-filter-based vocoders. Particularly, generated speech waveforms from the combination of AR acoustic model and Wavenet vocoder achieved a similar score of speech quality to vocoded speech.

Jaegul Choo Korea University Shixia Liu Tsinghua University Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever. However, even with such unprecedented advancements, the lack of explanation regarding the decisions made by deep learning models and absence of control over their internal processes act as major drawbacks in critical decision-making processes, such as precision medicine and law enforcement. In response, efforts are being made to make deep learning interpretable and controllable by humans. In this paper, we review visual analytics, information visualization, and machine learning perspectives relevant to this aim, and discuss potential challenges and future research directions. Deep learning has had a considerable impact on various long-running artificial intelligence problems, including computer vision, speech recognition and synthesis, and natural language understanding and generation [1].

Deep learning models, while effective and versatile, are becoming increasingly complex, often including multiple overlapping networks of arbitrary depths, multiple objectives and non-intuitive training methodologies. This makes it increasingly difficult for researchers and practitioners to design, train and understand them. In this paper we present ANNETT-O, a much-needed, generic and computer-actionable vocabulary for researchers and practitioners to describe their deep learning configurations, training procedures and experiments. The proposed ontology focuses on topological, training and evaluation aspects of complex deep neural configurations, while keeping peripheral entities more succinct. Knowledge bases implementing ANNETT-O can support a wide variety of queries, providing relevant insights to users. In addition to a detailed description of the ontology, we demonstrate its suitability to the task via a number of hypothetical use-cases of increasing complexity.

"Clean water and health care and school and food and tin roofs and cement floors, all of these things should constitute a set of basics that people must have as birthrights."1 Obtaining clean water is a critical problem for much of the world's population. Testing and confirming a clean water source typically requires expensive test equipment and manual analysis of the results. For regions in the world in which access to clean water is a continuing problem, simpler test methods could dramatically help prevent disease and save lives. To apply artificial intelligence (AI) techniques to evaluating the purity of water sources, Peter Ma, an Intel Software Innovator, developed an effective system for identifying bacteria using pattern recognition and machine learning.

Surviving in the Coursera Deep Learning world means understanding and navigating through the jungle of technical terms. You're not % sure what AdaGrad, Dropout, or Xavier Initialization mean? Use this guide as a reference to freshen up your memory when you stumble upon a term that you safely parked in a dusty corner in the back of your mind. This dictionary aims to briefly explain the most important terms of the Coursera Deep Learning Specialization from Andrew Ng's deeplearning.ai. It contains short explanations of the terms, accompanied by links to follow-up posts, images, and original papers.

From digital assistants like Siri to Tesla's self-driving cars, artificial intelligence and deep learning (a type of machine learning) are churning out today's tech breakthroughs. As new innovations are released, more doors open up to leverage them in existing fields, like integrating facial recognition in iPhones or iOS apps. That said, taking the time to understand how these innovations operate is a smart move -- whether you plan to implement them as an app developer or merely use them at work. Learn the foundations of these groundbreaking fields with the Pay What You Want: AI & Deep Learning Bundle, which nets you a host of e-books and training courses for a price that you get to pick. Here's how the deal works: Simply pay what you want, and you'll instantly unlock one of the collection's ten resources.

When I tell people that I work at an AI company, they often follow up with "So what kind of machine learning/deep learning do you do?" This isn't surprising, as most of the market attention (and hype) in and around AI has been centered around Machine Learning, and its high profile subset, Deep Learning, and around Natural Language Processing, with the rise of the chatbot and virtual assistants. But while machine learning is a core component for artificial intelligence, AI is in fact more than just ML. So what does it really mean for an application to be "intelligent"? What does it take to create a system that is "artificially intelligent?

Reinforcement Learning (RL) is an area of machine learning, where an agent learns by interacting with its environment to achieve a goal.In this course, you will be introduced to the world of reinforcement learning. You will learn how to frame reinforcement learning problems and start tackling classic examples like news recommendation, learning to navigate in a grid-world, and balancing a cart-pole. You will explore the basic algorithms from multi-armed bandits, dynamic programming, TD (temporal difference) learning, and progress towards larger state space using function approximation, in particular using deep learning. You will also learn about algorithms that focus on searching the best policy with policy gradient and actor critic methods. Along the way, you will get introduced to Project Malmo, a platform for Artificial Intelligence experimentation and research built on top of the Minecraft game.

Deep reinforcement learning (DRL) is an exciting area of AI research, with potential applicability to a variety of problem areas. Some see DRL as a path to artificial general intelligence, or AGI, because of how it mirrors human learning by exploring and receiving feedback from environments. Recent successes of DRL agents besting human video game players, the well-publicized defeat of a Go grandmaster at the hands of DeepMind's AlphaGo, and demonstrations of bipedal agents learning to walk in simulation have all contributed to the general sense of enthusiasm about the field. Unlike supervised machine learning, which trains models based on known-correct answers, in reinforcement learning, researchers train the model by having an agent interact with an environment. When the agent's actions produce desired results, it gets positive feedback.

The goal of this work in progress is to address distributed deep learning under differential privacy using the teacher-student paradigm. In the setting, there are a number of distributed entities and one aggregator. Each distributed entity leverages deep learning to train a teacher network on sensitive and labeled training data. The knowledge of the teacher networks is transferred to the student network at the aggregator in a privacy-preserving manner that protects the sensitive data. This transfer results from training non-sensitive and unlabeled data. We also apply secure multi-party computation to securely combining the outputs of local machine learning, in order to update a global model.