Learn about artificial neural networks and how they're being used for machine learning, as applied to speech and object recognition, image segmentation, modeling language and human motion, etc. We'll emphasize both the basic algorithms and the practical tricks needed to get them to work well. There is an emphasis hands-on labs to fully explain and extend the curriculum.

Machine learning/AI Training Course duration

3 Days

Machine learning/AI Training Course outline

Introduction to the course - machine learning and neural nets

    The Perceptron learning procedure

An overview of the main types of neural network architecture

    The backpropagation learning procedure

Learning the weights of a linear neuron

    Learning feature vectors for words

Learning to predict the next word

    Object recognition with neural nets

In this module we look at why object recognition is difficult

    Optimization: How to make the learning go faster

We delve into mini-batch gradient descent as well as discuss adaptive learning rates

    Recurrent neural networks

This module explores training recurrent neural networks

    More recurrent neural networks

We continue our look at recurrent neural networks

    Ways to make neural networks generalize better

We discuss strategies to make neural networks generalize better

    Combining multiple neural networks to improve generalization

This module we look at why it helps to combine multiple neural networks to improve generalization

    Hopfield nets and Boltzmann machines

Restricted Boltzmann machines (RBMs)

    This module deals with Boltzmann machine learning

Stacking RBMs to make Deep Belief Nets

    Deep neural nets with generative pre-training

Modeling hierarchical structure with neural nets

Recent applications of deep neural nets