Course Information
Registration period
Year-round Recruitment
Course Level
Study Mode
Duration
11 Hour(s) 45 Minute(s)
Language
English
Taught by
Prof. Ryan Ahmed | 450K+ Students | Best-Selling Professor | 250K+ YouTube, SuperDataScience Team, Ligency
Rating
Course Overview
Master Tensorflow 2.0, Google’s most powerful Machine Learning Library, with 10 practical projects
Artificial Intelligence (AI) revolution is here and TensorFlow 2.0 is finally here to make it happen much faster! TensorFlow 2.0 is Google’s most powerful, recently released open source platform to build and deploy AI models in practice.
AI technology is experiencing exponential growth and is being widely adopted in the Healthcare, defense, banking, gaming, transportation and robotics industries. The purpose of this course is to provide students with practical knowledge of building, training, testing and deploying Artificial Neural Networks and Deep Learning models using TensorFlow 2.0 and Google Colab.
The course provides students with practical hands-on experience in training Artificial Neural Networks and Convolutional Neural Networks using real-world dataset using TensorFlow 2.0 and Google Colab. This course covers several technique in a practical manner, the projects include but not limited to:
(1) Train Feed Forward Artificial Neural Networks to perform regression tasks such as sales/revenue predictions and house price predictions
(2) Develop Artificial Neural Networks in the medical field to perform classification tasks such as diabetes detection.
(3) Train Deep Learning models to perform image classification tasks such as face detection, Fashion classification and traffic sign classification.
(4) Develop AI models to perform sentiment analysis and analyze customer reviews.
(5) Perform AI models visualization and assess their performance using Tensorboard
(6) Deploy AI models in practice using Tensorflow 2.0 Serving
The course is targeted towards students wanting to gain a fundamental understanding of how to build and deploy models in Tensorflow 2.0. Basic knowledge of programming is recommended. However, these topics will be extensively covered during early course lectures; therefore, the course has no prerequisites, and is open to any student with basic programming knowledge. Students who enroll in this course will master AI and Deep Learning techniques and can directly apply these skills to solve real world challenging problems using Google’s New TensorFlow 2.0.
Course Content
- 7 section(s)
- 85 lecture(s)
- Section 1 INTRODUCTION AND COURSE OUTLINE
- Section 2 BUILD YOUR FIRST SIMPLE PERCEPTRON (SINGLE NEURON) MODEL IN TF 2.0
- Section 3 BUILD A MULTI LAYER ARTIFICIAL NEURAL NETWORKS FOR REGRESSION TASKS
- Section 4 ARTIFICIAL NEURAL NETWORKS FOR CLASSIFICATION TASKS
- Section 5 DEEP LEARNING FOR IMAGE CLASSIFICATION
- Section 6 MODEL DEPLOYMENT USING TF SERVING
- Section 7 Congratulations!! Don't forget your Prize :)
What You’ll Learn
- Master Google’s newly released TensorFlow 2.0 to build, train, test and deploy Artificial Neural Networks (ANNs) models.
- Learn how to develop ANNs models and train them in Google’s Colab while leveraging the power of GPUs and TPUs.
- Deploy ANNs models in practice using TensorFlow 2.0 Serving.
- Learn how to visualize models graph and assess their performance during training using Tensorboard.
- Understand the underlying theory and mathematics behind Artificial Neural Networks and Convolutional Neural Networks (CNNs).
- Learn how to train network weights and biases and select the proper transfer functions.
- Train Artificial Neural Networks (ANNs) using back propagation and gradient descent methods.
- Optimize ANNs hyper parameters such as number of hidden layers and neurons to enhance network performance.
- Apply ANNs to perform regression tasks such as house prices predictions and sales/revenue predictions.
- Assess the performance of trained ANN models for regression tasks using KPI (Key Performance indicators) such as Mean Absolute error, Mean squared Error, and Root Mean Squared Error, R-Squared, and Adjusted R-Squared.
- Assess the performance of trained ANN models for classification tasks using KPI such as accuracy, precision and recall.
- Apply Convolutional Neural Networks to classify images.
- Sample real-world, practical projects:
- Project #1: Train Simple ANN to convert Celsius temperature reading to Fahrenheit
- Project #2 (Exercise): Train Feedforward ANN to predict Revenue/sales
- Project #3: As a real-estate consultant, predict house prices using ANNs (Regression Task)
- Project #4 (Exercise): As a business owner, predict Bike rental usage (Regression Task)
- Project #5: Develop Artificial Neural Networks in the medical field to perform classification tasks such as diabetes detection (Classification task)
- Project #6: Develop AI models to perform sentiment analysis and analyze online customer reviews.
- Project #7: Train LeNet Deep Learning models to perform traffic signs classification.
- Project #8: Train CNN to perform fashion classification
- Project #9: Train CNN to perform image classification using Cifar-10 dataset
- Project #10: Deploy deep learning image classification model using TF serving
Skills covered in this course
Reviews
-
VVineesh Mk
very good
-
FFredrik R Skoglund
Good content composition, though outdated code examples, which are expected to be updated to the same date as when course is stamped as updated.
-
AAleksandr Saitgalin
the code is outdated, you gotta figure out the way to fix it on your own, there's no solutions in the q&a as well, most of the questions are from years ago. also a lot of things aren't really explained, like what do different methods do and their parameters. e.g. the lecturer says try to increase the number of units, it results in decreased perfomance but he doesn't explain why it is the case
-
MMohammed Rahman
great course. Great projects
