In 2018, I organized and led a Deep Learning course for graduate students, covering fundamental concepts like linear and non-linear regression, and advanced techniques like convolutional neural networks. The course materials, developed using TensorFlow and Keras, are available on GitHub for wider accessibility.

GitHub Repository: https://github.com/amingolnari/Deep-Learning-Course

Deep Learning Course

Generate Fake Data with Deep Convolutional Network

Introduction

TensorFlow Hello World

• HelloWorld.py

  Basic Operations in TensorFlow

• Part 1 BasicOne.py
• Part 2 BasicTwo.py

  TensorFlow’s Eager API

• EagerAPI.py

  Load Data From Excel File with Pandas

• ReadDataXLSX.py

Basic Models

TensorFlow Linear Regression

• TFLinearRegression.py

TensorFlow nonLinear Regression

• TFnonLinearRegression.py

TensorFlow Moon Classification

• TFMoonClassification.py

TensorFlow Circle Classification and Visualize with TensorBoard

• TFCircleTensorBoard.py

Keras Circle Classification and Visualize with TensorBoard

• KerasClassificationTB.py

Deep Models

TensorFlow CNN Classification on MNIST Data

• TFConvNetMNIST.py

  Keras CNN Classification on MNIST Data

• KerasConvNetMNIST.py

Using Callback in Keras

Stop Training with validation loss Check

Change Learning Rate Per (n) Epoch

Save Learning Rate Per Epoch

• KerasCallback.py

(Dog vs Cat) Keras Generate Batches of Tensor Image Data from Directory

• KerasGenData.py

Keras Generative Adversarial Network (GAN) on MNIST Data

• KerasGAN.py

Google Colab Files

Keras Cifar10 Convolutional Neural Networks

• KerasCifar10.ipynb

Keras LSTM on IMDB Dataset

• KerasRNNimdb.ipynb

Save and Load Keras Model (Jason and HDF5)

• SaveLoadKerasModel.ipynb