TensorFlow 101: Introduction to Deep Learning

Name: TensorFlow 101: Introduction to Deep Learning
Rating: 4.1 (193 reviews)

Ready to build the future with Deep Neural Networks? Stand on the shoulder of TensorFlow and Keras for Machine Learning.

Created bySefik Ilkin Serengil

Last updated 5/2020

English

What you'll learn

You will be able to build deep learning models for different business domains in TensorFlow
You can distinguish classification and regression problems, apply supervised learning, and can develop solutions
You can also apply segmentation analysis through unsupervised learning and clustering
You can consume TensorFlow via Keras in easier way.
Informed about tuning machine learning models to produce more successful results
Learn how face recognition works

Course content

9 sections • 23 lectures • 3h 55m total length

What is a Perceptron?2:12
Hands-on Perceptron11:49
Testing regular perceptron for XOR Gate

Installing Tensorflow and Prerequisites on Windows6:03
This video includes installation of Deep Learning Framework Tensorflow and its prerequisites. Python 3.5.3, Anaconda 4.4.0 and Tensorflow 1.2.0 respectively on Windows 7 64-bit OS.
Jupyter notebook2:43
Jupyter notebook is a pretty cute editor to develop python and tensorflow code. In this video, we will mention how to use it.
Hello, TensorFlow! Building Deep Neural Networks Classifier Model12:39
In previous post, we've gotten TensorFlow up. In this video, we are going to mention how to build deep neural networks classifier with TensorFlow. Classification is applied on Exclusive OR (XOR) gate dataset.
Actually, XOR gate solution is hello world program for machine learning studies. We will also focus the reason of it.
Repository: https://github.com/serengil/tensorflow-101/tree/master/course
Building Deep Neural Networks Classifier for both AND and OR gates

Restoring and Working on Already Trained Deep Neural Networks In TensorFlow10:00
In this video, we have mentioned how to re-use already trained neural networks in TensorFlow. Thus, we can make predictions fast even though long learning time required systems.
Repository: https://github.com/serengil/tensorflow-101/
Importing Saved TensorFlow DNN Classifier Model in Java16:41
In previous lecture, we've mentioned how to re-use trained neural networks in TensorFlow.

In this video, we've mentioned how to load and re-use trained TensorFlow neural networks in external higher level systems such as Java. Learning is implemented in TensorFlow whereas predictions are made in Java. TensorFlow also supports to be used in C++.
Repository: https://github.com/serengil/tensorflow-101/

Building a DNN Regressor for Non-Linear Time Series in TensorFlow21:19
Until now, we have built deep neural networks classifiers. Neural networks can also build models for regression studies. Today, we will focus on how to build a deep neural networks regressor in TensorFlow. Sine wave non-linear time series dataset will be used in the study. Finally, we will mention to monitor time series forecasts in TensorBoard.
Repository: https://github.com/serengil/tensorflow-101/
Visualizing ML Results with matplotlib and Embedding in TensorBoard9:34
Until now, we have mentioned the out of the box drawing capabilities of TensorFlow and TensorBoard for monitoring. We can also consume python matplotlib library to monitor results of machine learning studies.
Repository: https://github.com/serengil/tensorflow-101/
Importing Saved DNNRegressor Model in Java

Unsupervised learning and k-means clustering with TensorFlow12:05
Even though TensorFlow is developed as a Deep Learning Framework, it is also powerful about other ML algorithms. Today, we will mention how to handle unsupervised learning with TensorFlow. And we will apply k-means clustering algorithm a dataset. Also, we will use matplotlib to visualize clusters.
Repository: https://github.com/serengil/tensorflow-101/
Applying k-means clustering to n-dimensional datasets in TensorFlow5:35
In this video, we'll apply k-means clustering algorithm to n-dimensional wine data set in TensorFlow and visualize it in 3D.
Repository: https://github.com/serengil/tensorflow-101/

Optimization Algorithms in TensorFlow7:48
In this video, we will apply different optimization algorithms which are Gradient Descent, Adaptive Learning, Momentum and Adam (Adaptive Momentum) in TensorFlow and monitor loss changes and converge speed in TensorBoard.
Repository: https://github.com/serengil/tensorflow-101/
Activation Functions in TensorFlow7:51
In this video, we will mention activation functions in deep neural networks. Also, we will focus on that what makes these function common. Finally, we will monitor loss change (mean squared error) for these functions in TensorBoard.

After all, softplus funtion would be winner for xor gate classification among sigmoid, tanh and relu.
Repository: https://github.com/serengil/tensorflow-101/
Applying different optimization algorithms while running regressor for sine wave
Applying different activation functions for sine wave example

Installing Keras3:35
In this video, we will install Keras. TensorFlow installation is expected before installing Keras.
Building DNN Classifier with Keras7:06
We will build a keras deep neural networks classifier. Classifier still runs on TensorFlow in background.
Storing and restoring a trained neural networks model with Keras8:57
In this video, we'll mention how to store a trained model and how to restore it in Keras

Handwritten Digit Recognition Using Neural Networks17:05
In this lecture, we would build a neural networks model to recognize handwritten digits.
Handwritten Digit Recognition Using Convolutional Neural Networks with Keras18:58
Previously, we've applied fully connected neural networks to recognize handwriten digits. As an alternative to this approach, we can use convolutional neural networks (CNN) to do same duty. Training complexity reduces whereas more accurate predictions can be made with CNN.
Transfer Learning: Consuming InceptionV3 to Classify Cat and Dog Images in Keras10:06
Keras supports common image classifiers such as Inception, VGG and ResNet. We would consume these high level classifiers' pre-constructed structures and pre-trained weights to classify images as cat or dog.
Tips and Tricks for Transfer Learning7:07
Autoencoders10:35
Face Recognition11:35

Requirements

Familiar with machine learning concepts
Basic Python

Description

This course provides you to be able to build Deep Neural Networks models for different business domains with one of the most common machine learning library TensorFlow provided by Google AI team. The both concept of deep learning and its applications will be mentioned in this course. Also, we will focus on Keras.

We will also focus on the advanced topics in this lecture such as transfer learning, autoencoders, face recognition (including those models: VGG-Face, Google FaceNet, OpenFace and Facebook DeepFace).

This course appeals to ones who interested in Machine Learning, Data Science and AI. Also, you don't have to be attend any ML course before.

Who this course is for:

One who interested in Machine Learning, Data Science and AI
Anyone who would like to learn TensorFlow framework

TensorFlow 101: Introduction to Deep Learning

What you'll learn

Explore related topics

Course content

Perceptrons2 lectures • 14min

Introduction3 lectures • 21min

Reusability in TensorFlow2 lectures • 27min

Monitoring and Evaluating1 lecture • 14min

Building regression and time series models2 lectures • 31min

Building Unsupervised Learning Models2 lectures • 18min

Tuning Deep Neural Network Models2 lectures • 16min

Consuming TensorFlow via Keras3 lectures • 20min

Advanced applications6 lectures • 1hr 15min

Requirements

Description

Who this course is for: