- Module 1: Learn how to build a machine learning model using Keras
- Learn to load and prepare data to be used in machine learning.
- Learn to specify the architecture of a deep learning neural network.
- Learn to train a neural network.
- Learn to make a prediction using a neural network.
- Module 2: Learn how to perform different computer vision tasks using TensorFlow.
- Learn how to build computer vision machine learning models
- Learn how to represent images as tensors
- Learn how to build Dense Neural Networks and Convolutional Neural Networks
- Module 3: In this module, we'll explore different neural network architectures for processing natural language texts. Natural Language Processing (NLP) has experienced fast growth and advancement primarily because the performance of the language models depends on their overall ability to "understand" text and can be trained using an unsupervised technique on large text corpora. Additionally, pre-trained text models (such as BERT) simplified many NLP tasks and has dramatically improved the performance. We'll learn more about these techniques and the basics of NLP in this learning module.
- Understand how text is processed for natural language processing tasks
- Get an introduced to Recurrent Neural Networks (RNNs) and Generative Neural Networks (GNNs)
- Learn about Attention Mechanisms
- Learn how to build text classification models
- Module 4: Learn how to do audio classification with TensorFlow.
- Learn the basics of audio data
- Learn how to visualize and transform audio data
- Build a binary classification speech model that can recognize "yes" and "no"
- Module 5: Learn how to build a machine learning model using TensorFlow.
- Learn basic TensorFlow topics, such as tensors, variables and automatic differentiation.
- Learn the difference between eager and graph execution.
- Re-implement the train, test, and prediction phases of an existing Keras project using TensorFlow.
In this module you will:
In this module you will:
In this module you will:
In this module you will:
In this module you will:
