Reinforcement learning algorithms that can reliably learn how to control robots, etc. Better generative models. Algorithms that can reliably learn how to generate images, speech and text that humans can't tell apart from the real thing. Learning to learn and ubiquitous deep learning. Right now it still takes a human expert to run the learning-to-learn algorithm, but in the future it will be easier to deploy, and all kinds of businesses that don't specialize in AI will be able to leverage deep learning. More cyberattacks will leverage machine learning to make more autonomous malware, more efficient fuzzing for vulnerabilities, etc.
You might not know it, but deep learning already plays a part in our everyday life. When you speak to your phone via Cortana, Siri or Google Now and it fetches information, or you type in the Google search box and it predicts what you are looking for before you finish, you are doing something that has only been made possible by deep learning. Deep learning is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. It also is known as deep structured learning or hierarchical learning. The term Deep Learning was introduced to the machine learning community by Rina Dechter in 1986, and to Artificial Neural Networks by Igor Aizenberg and colleagues in 2000, in the context of Boolean threshold neurons.
The post coincides topically with last years' first annual Conference on Robot Learning as well as the workshop on Challenges in Robot Learning at NIPS2017, the latter we had the pleasure of co-organising together with colleagues from Oxford, DeepMind, and MIT. The events, as well as this post, cover current challenges and potentials of learning across various tasks of relevance in robotics and automation. In this context, similar to the long-term discussion on how much innate structure is optimal for artificial general intelligence, there is the more short-term question of how to merge traditional programming and learning (not sure if I prefer the branding as differentiable programming or software 2.0) for more narrow applications in efficient, robust and safe automation. The question about structure as beneficial or limiting aspect becomes arguably easier to answer in the context of robotic near-term applications as we can simply acknowledge our ignorance (our missing knowledge about what will work best in the future) and focus on the present to benchmark and combine the most efficient and effective directions. Existing solutions to many tasks in mobile robotics, such as localisation, mapping, or planning, focus on prior knowledge about the structure of our tasks and environments. This may include geometry or kinematic and dynamic models, which therefore have been built into traditional programs. However, recent successes and the flexibility of fairly unconstrained, learned models shift the focus of new academic and industrial projects. Successes in image recognition (ImageNet) as well as triumphs in reinforcement learning (Atari, Go, Chess) inspire like-minded research. As the post has become a bit of a long read, I suggest to read it like a paper: intro, discussion & conclusions and then - only if you did not fall asleep after all - the rest. Similar to scientific papers, some paragraphs will require basic familiarity with the field. However, a coarse web search should be enough to illustrate most unexplained terminology. Additionally, to keep this engaging, I have added some of my favourite recent videos highlighting interesting research for each section.
Artificial Intelligence (AI) has the opportunity to revolutionize the way the United States Department of Defense (DoD) and Intelligence Community (IC) address the challenges of evolving threats, data deluge, and rapid courses of action. Developing an end-to-end artificial intelligence system involves parallel development of different pieces that must work together in order to provide capabilities that can be used by decision makers, warfighters and analysts. These pieces include data collection, data conditioning, algorithms, computing, robust artificial intelligence, and human-machine teaming. While much of the popular press today surrounds advances in algorithms and computing, most modern AI systems leverage advances across numerous different fields. Further, while certain components may not be as visible to end-users as others, our experience has shown that each of these interrelated components play a major role in the success or failure of an AI system. This article is meant to highlight many of these technologies that are involved in an end-to-end AI system. The goal of this article is to provide readers with an overview of terminology, technical details and recent highlights from academia, industry and government. Where possible, we indicate relevant resources that can be used for further reading and understanding.
In [1, 2], we have explored the theoretical aspects of feature extraction optimization processes for solving large-scale problems and overcoming machine learning limitations. Majority of optimization algorithms that have been introduced in [1, 2] guarantee the optimal performance of supervised learning, given offline and discrete data, to deal with curse of dimensionality (CoD) problem. These algorithms, however, are not tailored for solving emerging learning problems. One of the important issues caused by online data is lack of sufficient samples per class. Further, traditional machine learning algorithms cannot achieve accurate training based on limited distributed data, as data has proliferated and dispersed significantly. Machine learning employs a strict model or embedded engine to train and predict which still fails to learn unseen classes and sufficiently use online data. In this chapter, we introduce these challenges elaborately. We further investigate Meta-Learning (MTL) algorithm, and their application and promises to solve the emerging problems by answering how autonomous agents can learn to learn? .