{"id":6808,"date":"2015-11-15T18:08:04","date_gmt":"2015-11-15T12:38:04","guid":{"rendered":"http:\/\/ucanalytics.com\/blogs\/?p=6808"},"modified":"2018-01-16T10:26:56","modified_gmt":"2018-01-16T04:56:56","slug":"learning-resources-artificial-intelligence-cognitive-computing-deep-learning-neural-networks","status":"publish","type":"post","link":"https:\/\/ucanalytics.com\/blogs\/learning-resources-artificial-intelligence-cognitive-computing-deep-learning-neural-networks\/","title":{"rendered":"Learning Resources : Artificial Intelligence, Cognitive Computing, Deep Learning, & Neural Networks"},"content":{"rendered":"

\"deep<\/a>This article is an effort to make you into a “semi-expert” in artificial intelligence, cognitive computing, deep learning and neural networks from scratch. Here I will share a few cool learning resources for these topics. These resources include documentaries, TED talks, online lecture videos, and books. There are several videos and online books included in this post to help you learn these concepts. These resources vary from introductory to advanced learning. These learning resources are organized under the following four categories<\/p>\n

1) Cognitive Computing and Artificial Intelligence <\/strong>\u2013\u00a0you will find some cool documentaries and TED talks in this section to get introduced to the fascinating world of AI and cognitive computing.<\/div>\n
2) Neural Networks Basics<\/strong> \u2013 neural networks are at the core of deep learning, cognitive computing, and AI. In this section, I will share a few videos\u00a0to demystify and learn neural networks.<\/div>\n
3) Deep Learning\u00a0Fundamentals<\/strong>\u00a0\u2013 In this section you will learn the fundamentals of deep learning from the best in academia i.e. researchers from\u00a0Stanford, Oxford, Montreal, and Toronto.<\/div>\n
4) Neural Networks and Deep Learning Practice Sessions<\/strong> \u2013\u00a0finally time for you to practice these new skills through working examples. Make sure you brush up your Python before this using this link \u2013 Book to learn Python<\/a><\/strong>.<\/div>\n

 <\/p>\n

However, before we jump towards these resources let’s visit the wonderland of data science which these fields are part of.<\/p>\n

Wonderland of\u00a0Data Science<\/span><\/h2>\n
\"The<\/a>

The Wonderland of Data Science – by Roopam<\/p><\/div>\n

The period between 1905-1930 was the golden age of\u00a0physics. Einstein, Bohr, Schrodinger, and other great minds\u00a0were working relentlessly on some of the greatest\u00a0ideas in physics including the General Theory of Relativity, and Quantum Mechanics. These ideas\u00a0shaped the direction for physics for the years to come. Similarly, Watson and Crick had ignited the golden age for biology and genetics in 1953 by discovering the double-helix structure of the DNA molecule. For chemistry, a similar\u00a0golden age was in the late 19th century initiated by Dmitri Mendeleev’s\u00a0periodic table.<\/p>\n

Every field of science goes through a golden age where a myriad of novel ideas is generated. These ideas not only shape the future of the field but provide a quantum jump in human understanding about\u00a0their\u00a0surroundings and nature.\u00a0We are undoubtedly living in the golden age of data science, statistics, and machine learning. As a practitioner of data science for all these years, I will be honest, I feel like how Alice must have felt in Wonderland. There are new and fascinating ideas coming from everywhere. This statement by Alice explains the reality of being in Wonderland.<\/p>\n

\n

I knew who I was this morning, but I’ve changed a few times since then. <\/em><\/p>\n

\u2013Alice (Alice in Wonderland)<\/p>\n<\/blockquote>\n

Evolution of Data Science<\/span><\/h2>\n

Risk and marketing models were\u00a0the pioneers of data science in industry. Like most professionals of data science, I started my career building these models and still do. Through them, I have learned a great deal\u00a0about sociology and social-psychology. These models are still extremely prominent for most industrial applications. But one of the key features about Wonderland is that it is always changing. In the wonderland of data science, one of the new directions is cognitive computing and artificial intelligence. AI has been\u00a0around in movies for a long time. However, it is becoming a reality\u00a0now with the advent of machine learning.<\/p>\n

There is\u00a0a faction that will argue that machine learning &\u00a0cognitive computing is not data science. The reason for their belief is since some machine learning models are like black boxes. These black box models don’t explain intuitive cause and effect relationship between predictor and target variables. I think this is a highly myopic view. This is like saying Quantum Mechanics is not physics or the General Theory of Relativity is not physics since they have different approaches to understand physical phenomena. To me, data science is an act of generation of\u00a0knowledge\/intelligence through data\/experience. Hence, both causal models and black box models are part of this wonderland of data science.<\/p>\n

In this article as promised earlier, I am going to share some\u00a0cool learn resources for artificial Intelligence, cognitive computing, and deep learning. Neural networks are at the root of these topics. Please also read an earlier article on YOU CANalytics about\u00a0artificial neural networks<\/a>.\u00a0Neural networks are inspired by our brain and are referred as black box models. Let me explain how\u00a0black box models work.<\/p>\n

Chicken Sexing & Neural Networks – Black Box Models<\/span><\/h2>\n

\"baby-chick-and-an-egg\"<\/a>Imagine you run a large commercial\u00a0poultry\u00a0farm. For a purely commercial purpose, it is absolutely important for you to distinguish between male and female chick right after hatching. You will keep all the female chicks for the production of eggs and a few male chicks. Most of the other male chicks will be killed immediately afterward. Now, the task of distinguishing male and female chicks is not at all easy because they all look almost exactly the same. It requires a trained professional called ‘chick sexer’ – I am not kidding\u00a0that’s a real name for the profession. Chick-sexers\u00a0use a method called vent sexing. This requires a\u00a0close examination of\u00a0the chicks’ rear to\u00a0classify them as male or female.<\/p>\n

A master chick sexer is extremely accurate in\u00a0classifying\u00a0sex.\u00a0However, even the best chick sexers won’t be able to explain their method for you to learn. Chicken sexing is a black box model where chick sexers do their job perfectly without knowing how they are doing it. The training for an apprentice chick sexer is equally fascinating. The master chick sexer overlooks the apprentice while the apprentice performs his task of distinguishing chicks. The master just provides a feedback of just yes or\u00a0no for each distinction the apprentice makes. This simple feedback loop and\u00a0a few months of rigorous effort, hardcodes the art of chicken sexing in the apprentice’s brain. Now the apprentice is ready to take over\u00a0from\u00a0his master without knowing how he did it.<\/p>\n

Knowledge and Awareness\u00a0<\/span><\/h2>\n

This creates a clear distinction between knowledge and awareness. It is not necessary that all knowledge leads to awareness. Similarly, some data science models (cause and effect models) produce awareness or provide reasons for how things work. The other data science models, like neural networks, produce knowledge without awareness. They are black box models like chicken sexing. Neural networks are at the core of deep learning algorithms. Moreover, deep learning algorithms are at the core of\u00a0most of the modern cognitive computing and systems with artificial intelligence.<\/p>\n

In the following sections, I will introduce learning resources\u00a0for artificial intelligence, cognitive computing, deep learning,\u00a0and neural networks.<\/p>\n

Artificial Intelligence and Cognitive Computing –\u00a0Get Excited<\/span><\/h2>\n

Cognitive computing is a subset of a broader\u00a0field called artificial intelligence. Cognitive computing facilitates applications that are\u00a0classified under artificial intelligence. At present, the toughest problems in cognitive computing involve tasks that humans can perform effortlessly\u00a0such as understanding languages, images, sound, and emotions.<\/p>\n

\"\"<\/p>\n

AlphaGo Zero: Starting from scratch<\/strong><\/p>\n

– DeepMind’s Professor David Silver describes AlphaGo Zero<\/em><\/p>\n

YOU CANalytics\u00a0Rating \"4 (4 \/ 5)<\/p>\n

Run Time:\u00a0~2:13 mins<\/p><\/blockquote>\n

Unlike real-life, games have well-defined rules. This makes them a great way to improve machine learning algorithms and cognitive computing. It all started with Deep Blue when it defeated Gary Kasparov in a chess duel. Then came IBM Watson which defeated the human champions of Jeopardy.\u00a0AlphaGo Zero is the latest and most powerful addition to this list. Unlike Deep Blue and Watson, AlphaGo Zero learns on its own by simulating games and data. This is explained in this 2 minutes video by\u00a0Professor David Silver of DeepMind. If you are interested in learning details about AlphaGo Zero algorithms then you could find it in this\u00a0paper.<\/a><\/p>\n

 <\/p>\n