If you've never used an object-oriented programming language before, you'll need to learn a few basic concepts before you can begin writing any code. This lesson will introduce you to objects, classes, inheritance, interfaces, and packages. Each discussion focuses on how these concepts relate to the real world, while simultaneously providing an introduction to the syntax of the Java programming language. An object is a software bundle of related state and behavior. Software objects are often used to model the real-world objects that you find in everyday life.

On a summer day four years ago, a Stanford University computer-science professor named Andrew Ng held an unusual air show on a field near the campus. His fleet of small helicopter drones flew under computer control, piloted by artificial-intelligence software that could teach itself to fly after watching a human operator. By the end of the day, the copters were hot-dogging--flipping, rolling, even hovering upside down. It was a milestone for the field of "machine learning," the same area of artificial intelligence that lets Amazon recommend books based on a shopper's previous habits and helps Google tailor search results to a user's behavior. Mr. Ng and his team of graduate students showed that artificial-intelligence software could control one of the hardest-to-maneuver vehicles and keep it stable while flying at 45 miles an hour.

Free Online AI course, Berkeley's CS 188, offered through edX. Free Online AI course, Berkeley's CS 188, offered through edX.

Want to watch this again later? Report Need to report the video? Report Need to report the video? Need to report the video? This feature is not available right now.

This lecture will cover recurrent neural networks, the key ingredient in the deep learning toolbox for handling sequential computation and modelling sequences. It will start by explaining how gradients can be computed (by considering the time-unfolded graph) and how different architectures can be designed to summarize a sequence, generate a sequence by ancestral sampling in a fully-observed directed model, or learn to map a vector to a sequence, a sequence to a sequence (of the same or different length) or a sequence to a vector. The issue of long-term dependencies, why it arises, and what has been proposed to alleviate it will be core subject of the discussion in this lecture. This includes changes in the architecture and initialization, as well as how to properly characterize the architecture in terms of recurrent or feedforward depth and its ability to create shortcuts or fast propagation of gradients in the unfolded graph. Open questions regarding the limitations of training by maximum likelihood (teacher forcing) and ideas towards towards making learning online (not requiring backprop through time) will also be discussed.

As the artificial intelligence space in Montreal heats up, a group of McGill student entrepreneurs are set to launch the McGill Artificial Intelligence Society. The McGill AI Society describes themselves as "a community of passionate students [who are] all about learning, practicing and sharing knowledge of the increasingly interesting field of AI." Led by Théo Szymkowiak, a third year McGill Computer Science student and former CTO of Fractal (McGill X-1 Cohort 2016), the McGill AI Society aims to provide introductory and advanced classes on Machine Learning and Artificial Intelligence where members will learn how to build robots, code up image classifiers, learn about speech recognition, and much more. McGill AI Society members will also have the opportunity to present their work and teach other students as well. This society is open to all McGill students from every faculty. Interested McGill students can register to be part of the McGill AI Society here.

Prerequisites: No prerequisites, knowledge of some undergraduate level mathematics would help but is not mandatory. Working knowledge of Python would be helpful if you want to run the source code that is provided. Taught by a Stanford-educated, ex-Googler and an IIT, IIM - educated ex-Flipkart lead analyst. This team has decades of practical experience in quant trading, analytics and e-commerce. The course is shy but confident: It is authoritative, drawn from decades of practical experience -but shies away from needlessly complicating stuff.

When the world's smartest companies such as Microsoft, Google, Alphabet Inc., and Baidu are investing heavily in Artificial Intelligence (AI), the world is going to sit up and take notice. Chinese Internet giant Baidu spent USD1.5 billion on research and development. And as proof of China's strong focus on AI and Machine Learning, Sinovation Ventures, a venture capital firm, invested USD0.1 billion in "25 AI-related startups" in the last three years in China and the U.S. Research shows that although genuine intelligence may still be a bit far off, AI and Machine Learning technologies are still expected to reign in 2017. Try reading up on Microsoft Project Oxford, IBM Watson, Google Deep Mind, and Baidu Minwa, and you'll understand what I am trying to get at. In 2015, Gartner's Hype Cycle for Emerging Technologies introduced Machine Learning (ML), and the graph showed (Figure 1) that it would reach a plateau in 2 to 5 years.

The scientist behind Google Glass wearable technology has criticised the use of restrictive and "fear-based" testing regimes in education, describing a lack of innovation in the system as a crisis. Sebastian Thrun, who led the Google research lab responsible for self-driving cars and Google Glass, made the comments ahead of a meeting with education minister Michael Gove. Thrun, who is one of the world's most influential computer scientists, is exploring online collaborative education – known as Moocs, which stands for "massively open online courses". He has developed a project called Udacity, which is working with two colleges and workplace learning schemes. "The education system is based on a framework from the 17th and 18th century that says we should play for the first five years of life, then learn, then work, then rest and then die. I believe we should be able to do all those things all the time," said Thrun.

Whether you're new to automation or are an experienced user, Automate has the solutions for you! Taking place April 3-6, 2017 at McCormick Place in Chicago, Automate offers the opportunity to connect with industry experts and over 300 exhibitors. While at the show, be sure to attend the Automate Conference, featuring the 48th Annual International Symposium on Robotics. The Automate Conference offers everything from a basic understanding of automation to more advanced topics in courses taught by industry professionals. To learn more about Automate and to register for the show and conference, visit the Automate website.