Given how artificial intelligence is a buzzing topic, it has sparked a slew of beginner-friendly introductory resources that clear the general concepts from this very broad topic. And for most newcomers, the most interesting topic in AI is Deep Learning. In fact, Google’s Python-based Deep Learning framework Tensorflow has helped many a developer get up to speed with the technical concepts. Besides videos and free online courses, you must also have a reading list that helps you cover the math and statistics behind the algorithms.
While YouTube videos remain the main learning source and a key starting point for beginners, there is a slew of resources, especially books that can help cement fundamental concepts.
Sign up for your weekly dose of what's up in emerging technology.
The Beginner’s Learning Path
Students who wish to do a beginner-level programme will find Python a good programming language to start with. Genetic algorithms with Python gives a hands-on introduction to genetic algorithms to business applications and also gives a step-by-step tutorial on how to use Python for solving specific problems. Scroll down to download the sample chapters here. In fact, the final code from each chapter is available for download using a link at the end of the chapter.
Introduction to Artificial Intelligence by Philip C Jackson is also a wonderful read on the fundamental concepts of artificial intelligence such as natural language representation and models, game playing, automated understanding of natural languages, robot systems, heuristic scene analysis. The book also covers a host of subjects such as machine architecture, industrial automation, predicate-calculus theorem proving, psychological simulation and new software techniques.
MIT: Another great introductory resource at the beginner level is MIT’s Open Courseware which doesn’t require learners to have any prerequisites. But one must have basic Python programming knowledge. The open courseware covers a bunch of topics such as text classification, search algorithms, neural nets, deep neural nets, support vector machines. However, the open courseware is a good starting point but it is also a bit outdated now. It doesn’t cover the new concepts but the learning outcome would be developers building a text classifier.
BAIR: The Berkeley Artificial Intelligence Research (BAIR) provides a great repository of learning materials with videos and slides on advanced applications such as NLP, games and cars, perceptrons, kernels and clustering. It also features a bunch of projects on Python, reinforcement learning, classification, multi-agent search.
Google AI: Since Google launched its free AI program, developers are making the best use of free tools and resources to advance their skills and build exciting projects. Google AI features machine learning crash course with TensorFlow APIs and guides on machine learning that also detail Google’s best practices in the field. Developers can also benefit from a course in Deep Learning Nanodegree Foundation.
NVIDIA Deep Learning Institute: NVIDIA’s DLI offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning and accelerated computing. However, these mini-courses are not for free but are an excellent way to pick up the basics of applications for professional growth. In addition to DLI, NVIDIA’s Developer Program also gives access to the latest tools, software and information to develop NVIDIA applications. Vishal Dhupar, managing director, South Asia at NVIDIA, shared that the program enables the delivery of an extensive range of NVIDIA software and technologies to the developer community and two-way communication about issues, enhancements, usage and future needs.
Srikanth Varma Chekuri’s AppliedAI, a course for persons who have no background in AI or ML, is also a great resource.
Learning Machines 101: While this free resource doesn’t give a lowdown on programming concepts or deep learning in any way, it is a good podcast on the fundamentals of AI. From technical notes to episode transcripts, the podcast covers topics such as How to design gradient descent learning machines and How to identify facial emotion expressions using stochastic neighbourhood embedding. You will also get a rundown on recent papers discussed at popular conferences.
Interestingly, Siraj Ravel’s YouTube channel has been voted as an interesting learning path, even though the online tutor has been panned for not covering the topics in-depth. As developers put it, one can always go back to the video to code over again and learn how to write AI programs effectively.
You can also check out Google Fellow Sebastian Thrun’s free MOOC on Introduction of AI here. Thrun is well-known for his work in robotics and self-driving technology and his courses draw a huge audience.