Applications of Deep Neural Networks for TensorFlow and Keras

Washington University in St. Louis via YouTube

Start learning Write review

Details

Start learning

Provider

YouTube
Pricing

Free Online Course
Languages

English
Duration & workload

17 hours
Sessions

On-Demand

Found in

Overview

This course on Applications of Deep Neural Networks for TensorFlow and Keras aims to teach learners the following: - Understanding and implementing deep learning concepts using Python, Keras, and TensorFlow - Applying deep neural networks for various tasks such as image processing, text generation, and reinforcement learning - Utilizing techniques like regularization, dropout, and transfer learning to improve model performance - Building and deploying deep learning models for real-world applications The course covers a wide range of skills and tools including: - Python programming for deep learning - Pandas for data manipulation - Keras and TensorFlow for building neural networks - Image processing techniques for neural networks - Transfer learning for feature engineering - Natural language processing with Spacy and Keras - Reinforcement learning with Q-Learning and TF-Agents - Web services integration with Flask and deep learning models - Automated machine learning (AutoML) for TensorFlow and Keras The teaching method involves a combination of video lectures, hands-on assignments, and practical applications to reinforce learning. The course is designed for individuals interested in deep learning, neural networks, and their applications in various domains such as computer vision, natural language processing, and reinforcement learning.

Syllabus

Deep Learning Course with Python, Keras and TensorFlow with Applications of Deep Neural Networks..
Applications of Deep Neural Networks Course Overview (1.1, Fall 2021).
Introduction to Python for Deep Learning (1.2).
Python Lists, Dictionaries, Sets & JSON (1.3).
Python File Handling for Deep Learning (1.4).
Python Functions, Lambdas, and Map/Reduce (1.5).
2021, Installing TensorFlow 2.5, Keras, & Python 3.9 in Mac OSX M1.
Installing TensorFlow/Keras CPU/GPU w/CONDA (July, 2020).
2021, Installing TensorFlow 2.4, Keras, & Python 3.8 in Mac OSX Intel.
Using Google CoLab for the Course Applications of Deep Neural Networks.
How to Submit Assignment for Application of Deep Learning (2020 update).
Introduction to Pandas for Deep Learning (2.1).
Encoding Categorical Values in Pandas for Keras (2.2).
Grouping, Sorting, and Shuffling in Python Pandas (2.3).
Using Apply and Map in Pandas for Keras (2.4).
Feature Engineering in Pandas for Deep Learning in Keras (2.5).
Deep Learning and Neural Network Introduction with Keras (3.1).
Introduction to Tensorflow & Keras for Deep Learning with Python (3.2).
Saving and Loading a Keras Neural Network (3.3).
Early Stopping in Keras to Prevent Overfitting (3.4).
Extracting Keras Weights and Manual Neural Network Calculation (3.5).
Encoding a Feature Vector for Keras Deep Learning (4.1).
Keras Multiclass Classification for Deep Neural Networks with ROC and AUC (4.2).
Keras Regression for Deep Neural Networks with RMSE (4.3).
Backpropagation, Nesterov Momentum, and ADAM Training (4.4).
Neural Network RMSE and Log Loss Error Calculation from Scratch (4.5).
Introduction to Regularization: Ridge and Lasso (5.1).
Using K-Fold Cross Validation with Keras (5.2).
Using L1 and L2 Regularization with Keras to Decrease Overfitting (5.3).
Drop Out for Keras to Decrease Overfitting (5.4).
Bootstrapping and Benchmarking Hyperparameters (5.5).
Image Processing in Python for Keras Neural Networks (6.1).
Keras Convolutional Neural Neural Networks for MNIST and Fashion MNIST (6.2).
Implementing a ResNet in Keras (6.3).
Using your own Images with Keras (6.4).
Recognizing Multiple Images with YOLO Darknet (6.5).
Introduction to Generative Adversarial Neural Networks (GANs) for Image and Data Generation (7.1).
Generating Faces with a Generative Adversarial Networks (GAN) in Keras/Tensorflow 2.0 (7.2).
Face Generation with NVIDIA StyleGAN2-ADA PyTorch and Python 3 (7.3).
GANS for Semi-Supervised Learning in Keras (7.4).
Some New Topics in the area of Generative Adversarial Network (GAN) Research (7.5).
Introduction to Kaggle (8.1).
Building Ensembles with Scikit-Learn and Keras (8.2).
How Should you Architect Your Keras Neural Network: Hyperparameters (8.3).
Bayesian Hyperparameter Optimization for Keras (8.4).
Spring 2020 Kaggle Competition for Applications of Deep Learning (8.5).
Introduction to Keras Transfer Learning (9.1).
Popular Pretrained Neural Networks for Keras (9.2).
Transfer Learning for Computer Vision and Keras (9.3).
Transfer Learning for Languages and Keras (9.4).
Transfer Learning for Keras Feature Engineering (9.5).
Time Series Data Encoding for Deep Learning, TensorFlow and Keras (10.1).
Programming LSTM with Keras and TensorFlow (10.2).
Text Generation with Keras and TensorFlow (10.3).
Image Captioning with Keras and TensorFlow (10.4).
Temporal Convolutional Neural Networks in Keras (10.5).
Getting Started with Spacy in Python (11.1).
Word2Vec and Text Classification (11.2).
What are Embedding Layers in Keras (11.3).
Natural Language Processing with Spacy and Keras (11.4).
Learning English from Scratch with Keras and TensorFlow (11.5).
Introduction to the OpenAI Gym (12.1).
Introduction to Q-Learning for Game Play (12.2).
Keras Q-Learning in the OpenAI Gym (12.3).
Atari Games with Keras TF-Agents (12.4).
Reinforcement Learning for Non-Games TF-Agents (12.5).
Flask and Deep Learning Keras/TensorFlow Web Services (13.1).
Resuming Training and Checkpoints in Python TensorFlow Keras (13.2).
Using a Keras Deep Neural Network with a Web Application (13.3).
When to Retrain Your Neural Network (13.4).
TensorFlow Lite for IOS Development (13.5).
Automated Machine Learning (AutoML) for Keras and TensorFlow (14.1).
Using Denoising AutoEncoders in Keras (14.2).
Anomaly Detection in Keras with AutoEncoders (14.3).
Training an Intrusion Detection System with Keras and KDD99 (14.4).
New Deep Learning Technology for Course (14.5).