AI: Advanced Machine Learning - Take Your Machine Learning Skills To The Next Level
Learn Advanced Machine Learning features to provide flexible, robust and efficient solutions
Machine Learning is one of the hottest topics in this century - for good reasons. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI.
In this course, you will start by learning about model complexity, overfitting and underfitting. From there, our instructor will teach you about pipelines, advanced metrics and imbalanced classes, and model selection for unsupervised learning. This course also covers dealing with categorical variables, dictionaries, and incomplete data, and how to handle text data. Finally, you will learn about out of core learning, including the sci-learn interface for out of core learning and kernel approximations for large-scale non-linear classification.
If you’re ready to take on a brand new challenge, and learn about Advanced AI techniques that you’ve never seen before in traditional supervised machine learning, unsupervised machine learning, or even deep learning, then this course is for you.
See you in class!
Course Curriculum
-
StartLecture 1 Welcome (3:28)
-
StartLecture 2 Prerequisites (2:13)
-
StartLecture 3 The Classifier Interface (8:29)
-
StartLecture 4 The Regressor Interface (2:53)
-
StartLecture 5 The Transformer Interface (2:11)
-
StartLecture 6 The Cluster Interface (6:04)
-
StartLecture 7 The Manifold Interface (3:32)
-
StartLecture 8 scikitLearn Interface Summary (4:01)
-
StartLecture 9 CrossValidation With Cross_Val_Score (6:18)
-
StartLecture 10 Parameter Searches With GridSearchCV (6:13)
-
StartLecture 11 What Is Model Complexity And Overfitting (2:58)
-
StartLecture 12 Linear Models InDepth (11:05)
-
StartLecture 13 Kernel SVMs InDepth (7:40)
-
StartLecture 14 Random Forests InDepth (6:02)
-
StartLecture 15 Learning Curves For Analyzing Model Complexity (3:53)
-
StartLecture 16 Validation Curves For Analyzing Model Parameters (2:30)
-
StartLecture 17 Efficient Parameter Search With EstimatorCV Objects (5:12)
Bill Gates Says These Are the Jobs He Would Drop Out of College for Today
If he were to go into computer sciences today, Gates said, the area that he thought had the most potential was artificial intelligence. Gates brought up a recent victory by Google DeepMind over the top player in the world at Go, a game some predicted a computer could never master. He called it a remarkable achievement that signaled there is more to come in advancement in artificial intelligence. And he said the research being done in the field now is "profound" and on the verge of making new breakthroughs. "The ability for artificial agents to read and understand material is going to be phenomenal," says Gates. "Anything connected with that would be an exciting lifetime career."