Practical Machine Learning with Tensorflow

COURSE OUTLINE: This will be an applied Machine Learning Course jointly offered by Google and IIT's. We will cover the basics of Tensorflow and Machine Learning in the initial sessions and advanced topics in the latter part. After this course, the students will be able to build ML models using Tensorflow.

Lecture 1: Overview of Tensorflow.
Lecture 2: Machine Learning Refresher.
Lecture 3: Steps in Machine Learning Process.
Lecture 4: Loss Functions in Machine Learning.
Lecture 5: Gradient Descent.
Lecture 6: Gradient Descent Variations.
Lecture 7: Model Selection and Evaluation.
Lecture 8: Machine Learning Visualization.
Lecture 9: Deep Learning Refresher.
Lecture 10: Introduction to Tensors.
Lecture 11: Mathematical Foundations of Deep Learning - Contd..
Lecture 12A: Building Data Pipelines for Tensorflow - Part 1.
Lecture 12B: Building Data Pipelines for Tensorflow - Part 2.
Lecture 12C: Building Data Pipelines for Tensorflow - Part 3.
Lecture 13: Text Processing with Tensorflow.
Lecture 14: Classify Images.
Lecture 15: Regression.
Lecture 16: Classify Structured Data.
Lecture 17: Text Classification.
Lecture 18: Underfitting and Overfitting.
Lecture 19: Save and Restore Models.
Lecture 20: CNNs-Part 1.
Lecture 21: CNNs-Part 2.
Lecture 22: Transfer learning with pretrained CNNs.
Lecture 23: Transfer learning with TF hub.
Lecture 24: Image classification and Visualization.
Lecture 25: Estimator API.
Lecture 26: Logistic Regression.
Lecture 27: Boosted Trees.
Lecture 28: Introduction to word embeddings.
Lecture 29: Recurrent Neural Networks Part 1.
Lecture 30: Recurrent Neural Networks Part 2.
Lecture 31: Time Series Forecasting with RNNs.
Lecture 32: Text Generation with RNNs.