Building Deep Learning Models with TensorFlow
Social Learning for Open Courses
Join one of our cohorts to learn from instructors, experts, or each other with weekly live streams.
-
Coursera
Uncommon Sense TeachingA Cohort with the acclaimed Instructor Barbara Oakley with 4+ million learners worldwide. This course weaves late-breaking insights from neuroscience with practical new approaches from the classroom.
Jan 17, 2022593 enrolled
-
University of Alberta
Science Friday: Black HolesBlack holes are fascinating and intriguing astronomical objects that capture our imagination. Astro 101, from University of Alberta, teaches us concepts such as astronomy, relativity, quantum physics, and much more.
Jan 03, 2022296 enrolled
Overview
Class Central Tips
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.
Syllabus
- 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. - 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.
- 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.
- 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.
- Unsupervised Deep Learning Models (Cont'd) and scaling
- In this module, you will mainly learn about autoencoders and their architecture.
Taught by
Alex Aklson
Related Courses
-
Deep Learning with Tensorflow
-
Introduction to Deep Learning & Neural Networks with Keras
-
Deep Learning With TensorFlow
-
Intro to TensorFlow for Deep Learning
3.3 -
Deep Learning and Reinforcement Learning
-
Machine Learning & Deep Learning Specialization with Python,Machine Learning & Deep Learning Specialization with Python"
Never Stop Learning!
