Oreilly - Neural Networks in Machine Learning for Developers
by Packt Publishing | Released January 2018 | ISBN: 9781789139792
Enhance your knowledge of Neural Networks About This VideoLearn to develop efficient and intelligent applications by leveraging the power of Machine LearningA highly practical guide explaining the concepts of problem solving in the easiest possible mannerImplement Machine Learning in the most practical wayIn DetailMost of us have heard about the term Machine Learning, but surprisingly the question frequently asked by developers across the Globe is, "How do I get started in Machine Learning?" One reason could be the vastness of the subject area because people often get overwhelmed by the abstractness of ML and terms such as regression, supervised learning, probability density function, and so on. This systematic guide will teach you various Machine Learning techniques.You will start with the very basics of neural networks and types. Then we learn about powerful variations in neural networks and Recurrent Neural Networks. Finally, we conclude with a synthetic introduction to more advanced Machine Learning techniques, such as GANs and reinforcement learning. Show and hide more
- Chapter 1 : Neural Networks
- The Course Overview 00:02:21
- History of Neural Models 00:05:34
- Implementing a Simple Function 00:02:48
- Loss Function 00:04:29
- Chapter 2 : Convolutional Neural Networks
- Origin of Convolutional Neural Networks 00:04:46
- Implementing Discrete Convolution 00:04:32
- Deep Neural Networks 00:04:30
- Chapter 3 : Recurrent Neural Networks
- RNNs 00:02:30
- LSTM 00:04:11
- Univariate Time Series Prediction 00:03:01
- Chapter 4 : Recent Models and Developments
- GANs 00:02:21
- Reinforcement Learning 00:03:49
Show and hide more
TO MAC USERS: If RAR password doesn't work, use this archive program:
RAR Expander 0.8.5 Beta 4 and extract password protected files without error.
TO WIN USERS: If RAR password doesn't work, use this archive program:
Latest Winrar and extract password protected files without error.