Into the Unknown
Introduction to TensorFlowGoogle Quite a lot stuff of TensorFlow was distilled into this course, from the basics to advanced techniques. I guess some topics probably will make beginners confused, but will strike a chord with experienced developers. The course first introduced the layers of API, the very basic tensor and Variable. Then put much effort…
TensorFlow is an open-source, high-performance library for any numerical computation (not just for machine learning). For example, you could use TensorFlow to solve partial differential equations. In order to make TensorFlow work, you need to create directed graph, which represent the computation you want to do. In a graph, nodes represent mathematical operations, edges represent…
Deduction to supervised learning problem In tabular method, each Q(s, a) could be seen as a parameter. There are more parameters than states, because there are as many parameters for each state as the possible number of actions for each state. There are also situations where states include continuous components. It means we need a…
Value Iteration in real world n real world, we don’t have the state transition probability distribution or the reward function. You may try sampling them, but you will never know the exact probabilities of them. As the result, you can not compute the expectation of the action values. We want a new algorithm that would…
Reinforcement Learning SpecializationUniversity of Alberta Anyone who loves reinforcement learning should not miss this specialization. Thank you University of Alberta! My Specialization Certificate Courses I am Kesler Zhu, thank you for visiting. Checkout all of my course reviews at http://KZHU.ai
A Complete Reinforcement Learning System (Capstone)University of Alberta For moon landing, let’s build a complete Deep RL system. You will get hands dirty in an expected SARSA agent using neural networks as function approximation and Adam as optimizer, also don’t forget softmax and replay buffer, and later parameter study! What an achievement! But meanwhile – as Prof. Martha White and Prof. Adam White pointed out – this is only the “first step towards learning…
Prediction and Control with Function ApproximationUniversity of Alberta This course reaches the apex of the entire reinforcement learning specialization! Don’t even bother ? if you are not ready for supervised learning and neural networks. The last topics policy parameterization and Actor-Critic algorithm are really the shiny pearls of the crown. Love it. A round of applause to Prof. Martha White and Prof. Adam White. Thank you very…
Sample-based Learning MethodsUniversity of Alberta I had a terrific time! This course covers quite a few fundamental & crucial reinforcement learning algorithms: Temporal Difference, SARSA, Dyna-Q, their variants, and their relationship with Dynamic Programming, Monte Carlo covered in previous course. The well-prepared programming assignments are both challenging and enlightening – helping me comprehend those complicated algorithms. My…
Fundamentals of Reinforcement LearningUniversity of Alberta Many thanks to Prof. Martha White and Adam White for this great reinforcement learning course – I wish I could have done this when I was in university. The course teaches fundamental concepts like Bellman equations, dynamic programming , etc. All of them become crystal clear. Finally, 2020 is over, let’s keep learning in 2021. Happy…
How to Win a Data Science Competition (with Honors)Higher School of Economics This course rocks! ? I found many tips, tricks and techniques very useful, some of them are a bit challenging to me. exploratory data analysis (EDA) is critical; ensembles are powerful; various kinds of hyper-parameters and metrics optimizations are the devil hides in the detail. A successful machine learning model is more…
Deep Learning SpecializationDeepLearning.AI Mission complete! This is probably the most popular specialization on Coursera. Cutting-edge topics, high quality programming assignments鈥攂oth newbies and veterans can benefit. I found the knowledge learned can be used directly in daily work and also let me get prepared for the future. Thank you Andrew Ng, much obliged! My Specialization Certificate…
Sequence ModelsDeepLearning.AI When I finished this course, I picked up my phone and asked “Hey Siri, what is sequence model”? Guess what? She understand and she showed me web page of this course exactly. Pretty cool! This course reveals what is under the hood: recurrent neural network, word embedding, beam search, attention model, etc. I…
Convolutional Neural NetworksDeepLearning.AI This great course helps you grasp fundamentals of CNN and get familiar with the most recent hot applications (self-driving, face recognition, neural style transfer) in just a few weeks. Programming assignments are well-prepared, easy to complete, and more about how to leverage existing frameworks / algorithms / models (e.g. YOLO). You will have…
Applied Machine Learning in PythonUniversity of Michigan This is a nice course about scikit-learn – a stable, powerful and still indispensable library nowadays. The course covers many classic models, and how to use them efficiently. Various evaluation curves and model selection are what I like most. The comparison between scikit-learn with other new libraries (such…
Structuring Machine Learning ProjectsDeepLearning.AI This is a short-but-effective course about strategy. The topics are all critical for helping team analyze errors, select direction, make progress and archive goals effectively. The methods demonstrated when doing analysis are very impressive. I am afraid these knowledge will never be available in any academic textbook, you can only learn…