Log In
Or create an account ->
Imperial Library
Home
About
News
Upload
Forum
Help
Login/SignUp
Index
Introduction
Chapter One: Introducing Deep Learning
How Does Deep Learning Work?
What is a Deep Learning Neural Network?
Deep Learning Methods
Deep Learning Applications
Deep Learning Challenges and Limitations
Machine Learning vs. Deep Learning
A Brief History
Chapter Two: Python and Deep Learning
The Top Python Libraries for Deep Learning
Chapter Three: A Look At Neural Networks
Neural Network Applications
Examples of What Deep Learning Can Do
The Elements of a Neural Network
Feedforward Networks
Multiple Linear Regression
Gradient Descent
Logistic Regression
Chapter Four: A Deeper Look at Recurrent Neural Networks and LSTMs
More on Feedforward Networks
Recurrent Neural Networks
Backpropagation Through Time (BPTT)
Long Short-Term Memory Units (LSTMs)
Capturing Remote Dependencies and Diverse Time Scales
Chapter Five: Introduction To CNNs and Image Processing
Images as 4D Tensors
The Definition of Convolutional
How Do Convolutional Neural Networks Work?
Max Pooling/Downsampling
Chapter Six: An Introduction to Deep Reinforcement Learning
The Definitions of Reinforcement Learning
Domain Selection
Neural Networks and Deep Reinforcement Learning
Chapter Seven: Let’s Build a Deep Learning Model with Keras and TensorFlow
Step One – Data Pre-Processing
Step Two – Splitting Your Dataset
Step Three — Transform the Data
Step Four — Build the Neural Network
Step Five — Use the Test Set for Predictions
Step Six — Use a Confusion Matrix
Step Seven — Make One Prediction
Step Eight — Improve the Model Accuracy
Step Nine — Reduce Overfitting By Adding Dropout Regularization
Step Ten — Tune the Hyperparameters
Chapter Eight: Building a Neural Network With TensorFlow For Handwritten Digit Recognition
Step One — Configure Your Project
Step Two — Import the MNIST Dataset
Step Three — Define the Architecture of Your Neural Network
Step Four — Build the TensorFlow Graph
Step Five — Train and Test
Chapter Nine: How to Keep Your Deep Learning Models Bug-Free
Step One – Keep Things Simple
Step Two – Implement Your Model and Debug It
Step Three – Evaluate the Model Performance
Step Four – Improving Your Model and Data
Step Five - Tuning the Hyperparameters
Conclusion
← Prev
Back
Next →
← Prev
Back
Next →