English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 1h 45m | 400 MB
Over 20 practical videos on neural network modeling, reinforcement learning, and transfer learning using Python
Deep Learning is revolutionizing a wide range of industries. For many applications, Deep Learning has been proven to outperform humans by making faster and more accurate predictions. This course provides a top-down and bottom-up approach to demonstrating Deep Learning solutions to real-world problems in different areas.
These applications include Computer Vision, Generative Adversarial Networks, and time series. This course presents technical solutions to the issues presented, along with a detailed explanation of the solutions.
Furthermore, it provides a discussion on the corresponding pros and cons of implementing the proposed solution using a popular framework such as TensorFlow, PyTorch, and Keras. The course includes solutions that are related to the basic concepts of neural networks; all techniques, as well as classical network topologies, are covered. The main purpose of this video course is to provide Python programmers with a detailed list of solutions so they can apply Deep Learning to common and not-so-common scenarios.
This video course is a unique blend of independent solutions arranged in the most logical manner.
What You Will Learn
- Implement different neural network models in Python
- Select the best Python framework for Deep Learning such as PyTorch, Tensorflow, MXNet, and Keras
- Boost learning performance by applying tips and tricks related to neural network internals
- Consolidate machine learning principles and apply them in the Deep Learning field
- Reuse Python code snippets and adapt them to everyday problems
- Evaluate the cost/benefits and performance implication of each discussed solution
The course overview
Understanding TensorFlow, Keras and PyTorch Framework
Deep Learning Using CNTK and Gluon Framework
Implementing Single and Multi-Layer Neural Network
Experiment with Activation Functions, Hidden Layers, and Hidden Units
Autoencoder, Loss Function, and Optimizers
Overfitting Prevention Methods
Optimization Techniques for CNNs
Experimenting with Different Types of Initialization
Implementing Simple RNN and LSTM
Implementing GRUs and Bidirectional RNNs
Implementing Generative Adversarial Networks
Computer Vision Techniques
Detecting Facial Key Points and Transferring Styles
Hyper Parameter Selection and Tuning
Time Series and Structured Data
Visualizing and Analysing Network
Freezing and Storing the Network
Using InceptionV3 and ResNet50 Model
Leveraging VGG Model and Fine Tuning