Machine Learning with scikit-learn and Tensorflow

Course details

Machine Learning is one of the most transformative and impactful technologies of our time. From advertising to healthcare, to self-driving cars, it is hard to find an industry that has not been or is not being revolutionized by machine learning. Using the two most popular frameworks, Tensor Flow and Scikit-Learn, this course will show you insightful tools and techniques for building intelligent systems. Using Scikit-learn you will create a Machine Learning project from scratch, and, use the Tensor Flow library to build and train professional neural networks.

We will use these frameworks to build a variety of applications for problems such as ad ranking and sentiment classification. The course will then take you through the methods for unsupervised learning and what to do when you have limited or no labels for your data. We use the techniques we have learned, along with some new ones, to build a sentiment classifier, an autocomplete keyboard and a topic discoverer.

The course will also cover applications for Natural Language Processing, explaining the types of language processing. We will cover TensorFlow, the most popular deep learning framework, and use it to build convolutional neural networks for object recognition and segmentation. We will then discuss recurrent neural networks and build applications for sentiment classification and stock prediction. We will then show you how to process sequences of data with recurrent neural networks with applications in sentiment classification and stock price prediction. Finally, you will learn applications with deep unsupervised learning and generative models. By the end of the course, you will have mastered Machine Learning in your everyday tasks

All the code and supporting files for this course are available on Github.

About the Author

Nick Locascio is a deep learning consultant, writer, researcher, and entrepreneur. Nick attended MIT, where he obtained his B.S. and MEng conducting research in NLP and Computer Vision. He has worked on projects ranging from training neural networks that generate code, to collaborating with the MGH Radiology department to apply deep learning to assist in clinical screening mammography. Nick's work has been featured on MIT News and CNBC. Nick does private deep learning consulting for Fortune-500 enterprise companies. He also co-founded the landmark MIT course 6.S191, Intro to Deep Learning, which he taught to an audience of 300 students, post-docs, and professors. Nicks writing experience includes credits as a contributing author to Fundamentals of Deep Learning.