The majority of data in the world is unlabeled and unstructured. Shallow neural networks cannot easily capture relevant structure in, for instance, images, sound, and textual data. Deep networks are capable of discovering hidden structures within this type of data. In this course you’ll use TensorFlow library to apply deep learning to different data types in order to solve real world problems.
Class Deals by MOOC List - Click here and see Coursera's Active Discounts, Deals, and Promo Codes.
Learning Outcomes:
After completing this course, learners will be able to:
• explain foundational TensorFlow concepts such as the main functions, operations and the execution pipelines.
• describe how TensorFlow can be used in curve fitting, regression, classification and minimization of error functions.
• understand different types of Deep Architectures, such as Convolutional Networks, Recurrent Networks and Autoencoders.
• apply TensorFlow for backpropagation to tune the weights and biases while the Neural Networks are being trained.
Course 5 of 6 in the IBM AI Engineering Professional Certificate
Syllabus
WEEK 1
Introduction
In this module, you will learn about TensorFlow, and use it to create Linear and Logistic Regression models.
You will also learn about the fundamentals of Deep Learning.
WEEK 2
Supervised Learning Models
In this module, you will learn about about Convolutional Neural Networks, and the building blocks of a convolutional neural network, such as convolution and feature learning. You will also learn about the popular MNIST database. Finally, you will learn how to build a Multi-layer perceptron and convolutional neural networks in Python and using TensorFlow.
WEEK 3
Supervised Learning Models (Cont'd)
In this module, you will learn about the recurrent neural network model, and special type of a recurrent neural network, which is the Long Short-Term Memory model. Also, you will learn about the Recursive Neural Tensor Network theory, and finally, you will apply recurrent neural networks to language modelling.
WEEK 4
Unsupervised Deep Learning Models
In this module, you will learn about the applications of unsupervised learning. You will learn about Restricted Boltzmann Machines (RBMs), and how to train an RBM. Finally, you will apply Restricted Boltzmann Machines to build a recommendation system.
WEEK 5
Unsupervised Deep Learning Models (Cont'd)
In this module, you will mainly learn about autoencoders and their architecture.
