Advanced Neural Networks with Tensorflow

Watch Advanced Neural Networks with Tensorflow

  • 2018
  • 1 Season

Advanced Neural Networks with Tensorflow is a comprehensive video course that provides an in-depth understanding of how to build and train advanced neural networks using the popular open-source TensorFlow library. The course is designed for developers and data scientists who want to take their skills to the next level by learning cutting-edge neural network techniques and methods to develop faster, more efficient, and more accurate machine learning models.

The course consists of over 54 lectures, which are divided into six sections, each covering a specific topic. The course starts with an introduction to neural networks and the basics of TensorFlow, including the installation and setup of the library. The course then moves on to explore advanced neural network topics such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Autoencoders, and Generative Adversarial Networks (GANs) in detail. The course also covers topics such as Transfer Learning, Reinforcement Learning, and Natural Language Processing (NLP), enabling the students to develop complete end-to-end machine learning solutions.

The lectures are taught by an industry expert, who has hands-on experience in developing advanced neural networks using TensorFlow. The instructor not only provides theoretical knowledge but also offers practical insights into how to implement these techniques using real-world data. The course covers the best practices for hyperparameter tuning, regularization techniques, and how to debug and analyze the neural network models.

One of the most significant advantages of this course is that it is self-paced, allowing students to learn at their own pace. Students can start with the basics and gradually move towards more advanced topics. The course also includes several quizzes and assignments to test the students' knowledge and skills at each section.

The course is designed in such a way that it is suitable for both beginners who are new to neural networks and advanced users who want to learn the latest techniques in machine learning. The instructor starts with the basics and then gradually builds upon that knowledge to cover advanced topics. For example, in the CNN section, the instructor starts with the basics of CNNs and then moves on to explore topics such as Transfer Learning and Object Detection. Similarly, in the RNN section, the instructor covers the basics of RNNs and then moves on to explore topics such as Sequence to Sequence models and Attention Mechanisms.

One of the unique features of this course is the inclusion of real-world examples and applications of the techniques and methods. The instructor demonstrates how to use deep learning to solve real-world problems such as image classification, sentiment analysis, and language translation. These examples not only provide practical insights into how to apply the techniques but also help to reinforce the concepts learned in the course.

Overall, Advanced Neural Networks with TensorFlow is a comprehensive course that provides a deep understanding of how to build and train advanced neural networks using the popular TensorFlow library. The course covers a broad range of topics, including CNNs, RNNs, Autoencoders, and GANs, enabling students to develop complete end-to-end machine learning solutions. The self-paced nature of the course and the inclusion of real-world examples make it suitable for both beginners and advanced users. The course also includes several quizzes and assignments to test the students' knowledge and skills.

Advanced Neural Networks with Tensorflow is a series that is currently running and has 1 seasons (23 episodes). The series first aired on February 14, 2018.

Filter by Source

Seasons
Starting and Training a Session
25. Starting and Training a Session
February 14, 2018
In this video, we will start a session to set variables of two networks to the same value.
Defining Our Network
24. Defining Our Network
February 14, 2018
In this video, we will define our Neural Network.
Playing Atari Games
23. Playing Atari Games
February 14, 2018
In this video, we will use Deep Learning to play Atari games.
Reinforcement Learning Explained
20. Reinforcement Learning Explained
February 14, 2018
We will take a look at reinforcement learning, which is a technique where an autonomous agent learns by getting rewards whenever he does something good! We will discuss what q-learning is, and how deep q-networks work.
Random Search
19. Random Search
February 14, 2018
You could try to solve this environment with one simple matrix multiplication with the input. This essentially gives you a single Neural Network, but no way to optimize this with gradient descent.
Getting Started with the OpenAI Gym
18. Getting Started with the OpenAI Gym
February 14, 2018
We will install the OpenAI gym environment and explore the problem of balancing a stick on a cart.
Speed of Your Network
17. Speed of Your Network
February 14, 2018
We previously built a lot of large neural networks, and will continue to do so in the next section. In this video, we will analyze what factors influence the speed with which we train our Neural Network.
Alternative Loss Functions
16. Alternative Loss Functions
February 14, 2018
In this video, we will explore two different loss functions: a cross-entropy error on the last layer, and a contrastive loss function that works like a "spring".
Training and Testing a Siamese Neural Network
15. Training and Testing a Siamese Neural Network
February 14, 2018
We defined our network in the previous video. Now it's time to train and test it. We use the data load functions from the first video to train and evaluate our performance.
What Is a Siamese Neural Network?
14. What Is a Siamese Neural Network?
February 14, 2018
Siamese Neural Networks map input to an output vector. The idea is that this output is similar for similar characters. In this video, we will create such a network with TensorFlow.
The Omniglot Dataset
13. The Omniglot Dataset
February 14, 2018
We will look at the Omniglot dataset. This dataset contains many classes and 20 samples per class.
Variational Autoencoders
12. Variational Autoencoders
February 14, 2018
By setting the variables in the latent layer to random values, we could generate "new" images of characters. As we don't know in what range we could pick these values, we add an extra loss to our autoencoder that specifies the range we want.
The Dropout Layer
11. The Dropout Layer
February 14, 2018
It's often difficult to work with noisy input data. Neural Networks tend to "overfit" on certain patterns, which are disturbed by this noise. Dropout is an effective way to reduce your testing error.
Practical Application -Denoising
10. Practical Application -Denoising
February 14, 2018
In this video, we will take a look at the result of our decoder. We will also look at one practical application: denoising your input.
Encoding MNIST Characters
9. Encoding MNIST Characters
February 14, 2018
We will build our first autoencoder that is able to represent MNIST characters in only 10 values. We will evaluate if our neural network can learn something.
Inspecting Input and Output
8. Inspecting Input and Output
February 14, 2018
Sometimes the problem with your Neural Network is not in the network, but in the data you put into it (or get out of it). Luckily, we can inspect both with TensorBoard.
Plotting the Weights in a Histogram
7. Plotting the Weights in a Histogram
February 14, 2018
Sometimes you want to take a look at the value of your weights. We will compare two runs, one run with a wrong learning rate.
Adding Summaries
6. Adding Summaries
February 14, 2018
Now that we are able to get our graph in TensorBoard, it's time to add something more interesting, that is, the loss. With TensorBoard we can plot multiple lines in the same graph.
Visualizing Your Graph
5. Visualizing Your Graph
February 14, 2018
We will take a look at what TensorBoard is, and how to start it. Luckily TensorBoard is already included in the Dockerfile you are running.
Understanding Jupyter Notebooks and TensorFlow
4. Understanding Jupyter Notebooks and TensorFlow
February 14, 2018
In this video, viewers are shown how they can design a Neural Network that can recognize written digits with TensorFlow.
Installing Docker and Downloading the Source Code for This Course
3. Installing Docker and Downloading the Source Code for This Course
February 14, 2018
During this course, we will download one program with all dependencies using Docker. This video will show you what to download to set up your machine learning workspace.
The Approach of This Course
2. The Approach of This Course
February 14, 2018
There are a lot of different problems in machine learning you can approach with neural networks. In this section, we are going to learn about autoencoders, siamese Neural Networks, and reinforcement learning.
The Course Overview
1. The Course Overview
February 14, 2018
This video provides an overview of the entire course.
Description
Where to Watch Advanced Neural Networks with Tensorflow
Advanced Neural Networks with Tensorflow is available for streaming on the Packt Publishing website, both individual episodes and full seasons. You can also watch Advanced Neural Networks with Tensorflow on demand at Amazon.
  • Premiere Date
    February 14, 2018