Artificial Intelligence III - Deep Learning in Java

Deep Learning Fundamentals, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) + LSTM, GRUs

This course is about deep learning fundamentals and convolutional neural networks. Convolutional neural networks are one of the most successful deep learning approaches: self-driving cars rely heavily on this algorithm. First you will learn about densly connected neural networks and its problems. The next chapter are about convolutional neural networks: theory as well as implementation in Java with the deeplearning4j library. The last chapters are about recurrent neural networks and the applications - natural language processing and sentiment analysis!

So you'll learn about the following topics:

Section #1:

• multi-layer neural networks and deep learning theory

• activtion functions (ReLU and many more)

• deep neural networks implementation

• how to use deeplearning4j (DL4J)

Section #2:

• convolutional neural networks (CNNs) theory and implementation

• what are kernels (feature detectors)?

• pooling layers and flattening layers

• using convolutional neural networks (CNNs) for optical character recognition (OCR)

• using convolutional neural networks (CNNs) for smile detection

• emoji detector application from scratch

Section #3:

• recurrent neural networks (RNNs) theory

• using recurrent neural netoworks (RNNs) for natural language processing (NLP)

• using recurrent neural networks (RNNs) for sentiment analysis

These are the topics we'll consider on a one by one basis.

You will get lifetime access to over 40+ lectures!

This course comes with a 30 day money back guarantee! If you are not satisfied in any way, you'll get your money back. Let's get started!