Introduction to TensorFlow for Deep Learning

Welcome to our Introduction to TensorFlow for Deep Learning Course! We present you the 2-month program for TensorFlow enthusiasts in collaboration with Google. This is a totally FREE course.

According to Google: “TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.”

In this course you’ll get hands-on experience building your own state-of-the-art image classifiers and other deep learning models. You will use TF models on mobile application, you will learn advanced techniques and algorithms like CNNs, RNNs, LSTM to work with big data. Also, you will get intuition about working with time series and text data.

This is a self-paced learning course. You will study resources by yourself and we will increase your learning process by scheduling webinars with industry leading professionals and Q&A sessions, providing extra resources, quizzes and mentorship during the class.


Introduction to Machine Learning
  • What is ML?​
  • Dense Layers​
Your First Model: Fashion MNIST
  • Introduction​
  • Fashion MNIST Dataset
  • ​Neural Network
  • ​Training and Testing
  • Celsius and MNIST
Introduction to Convolutional Neural Networks (“CNNs”)​
  • Introduction
  • ​Convolutions
  • ​Max Pooling
  • Fashion MNIST vs CNN​
Going Further with CNNs​
  • Introduction​
  • Dogs and Cats Dataset​
  • Images for Different Size ​
  • Color Images Part 1​
  • Color Images Part 2
  • Convolutions with Color Images
  • Max Pooling with Color Images
  • Softmax and Sigmoid
  • Validation
  • Image Augmentation
  • Dropout
  • Other Techniques to Prevent Overfitting
Transfer Learning​
  • Introduction​
  • Transfer Learning​
  • MobileNet
  • Understanding Convolutional Neural Networks
Saving and Loading Models​ Time Series Forecasting​
  • Introduction​
  • Applications
  • Common Patterns​
  • Forecasting​
  • Metrics​
  • Time Windows​
  • Forecasting with Machine Learning
  • RNNs
  • Recurrent Layer​
  • Back Propagation Through Time​
  • Stateless and Stateful RNNs​
  • Implementing Stateful RNN​
  • LSTM Cells​
  • CNNS​
  • Padding​
  • Stride​
  • Kernels
  • WaveNet​
NLP: Tokenization and Embeddings​
  • Introduction to NLP​
  • Tokenizing Text​
  • Text to Sequence​
  • Tokenization of Large Dataset
  • Word Embeddings
  • Visualizing Embeddings
  • Tweaking the Model
  • Recurrent Neural Networks Intro​
  • Basic of RNNs
  • Sentence Context and LSTMs​
  • LSTMs vs. Convolutions vs. GRUs
  • ​Text Generation
  • ​Optimizing the Text Generation Model
Introduction to TensorFlow Lite​

Course Information

  Skill Level: Intermediate


  Languages: English

  Total Duration: 2 months

  Certification: Yes

  Free Course