This Specialization by Imperial College London provides practical skills in TensorFlow 2 for machine learning researchers and practitioners. The first course focuses on building, training, evaluating, and making predictions with deep learning models using the Sequential API. The second course delves into customizing deep learning models and workflows using lower level APIs and sequence models. The final course specializes in probabilistic approaches to deep learning, teaching how to quantify uncertainty and develop probabilistic models with TensorFlow Probability library.
Throughout the Specialization, participants will engage in hands-on coding tutorials, programming assignments, and Capstone Projects to apply their knowledge. The courses require proficiency in Python, general machine learning and deep learning concepts, and a solid foundation in probability and statistics, particularly for the third course.
Certificate Available ✔
Get Started / More Info
This Specialization comprises three courses. The first course covers fundamental concepts for developing deep learning models using the Sequential API, while the second course focuses on customizing models with lower level APIs and sequence models. The final course specializes in the probabilistic approach to deep learning, teaching how to develop probabilistic models with TensorFlow.
Welcome to the first course of the Specialization, "Getting started with TensorFlow 2." In this course, you will learn an end-to-end workflow for developing deep learning models with TensorFlow, starting from building, training, and evaluating models using the Sequential API. You will also gain practical experience in implementing regularisation, callbacks, and saving and loading models. The course culminates in a Capstone Project where you will develop an image classifier deep learning model from scratch.
Welcome to the second course, "Customising your models with TensorFlow 2." This course deepens your knowledge and skills with TensorFlow, enabling you to develop fully customized deep learning models and workflows for any application. You will utilize lower-level APIs to develop complex model architectures, custom layers, and a flexible data workflow. Additionally, you will expand your knowledge of the TensorFlow APIs to include sequence models. The course concludes with a Capstone Project where you will develop a custom neural translation model from scratch.
Welcome to the final course, "Probabilistic Deep Learning with TensorFlow 2." Building on the foundational concepts and skills from the first two courses, this course focuses on the probabilistic approach to deep learning. You will learn how to develop probabilistic models with TensorFlow, with a particular emphasis on using the TensorFlow Probability library. The course covers various topics, including developing models for uncertainty quantification and generative models. The course culminates in a Capstone Project where you will develop a variational autoencoder algorithm to produce a generative model of a synthetic image dataset.
Detect Fake News in Python with Tensorflow.
Learn to implement Linear Regression using Python and Numpy in this 2-hour project-based course.
Solve Business Problems with AI and Machine Learning equips learners with essential skills to apply AI and ML to real-world business challenges, select appropriate...
Enhance your content creation skills with a project-based course using Jasper AI to create a professional product review blog post for wireless noise-cancelling...