Course Description
Discover how to apply deep learning techniques to images, and how to leverage TensorFlow estimators in building image classification models.
Learning Objectives
TensorFlow: Deep Neural Networks and Image Classification
- Course Overview
- distinguish between traditional machine learning and deep learning
- recognize the architecture and design of a neural network
- identify what is meant by model weights or model parameters
- identify the precise operations performed by a neuron
- recognize gradient descent as the training process in a neural network
- distinguish between the operations in the forward and backward passes during training
- describe how images are fed into a machine learning algorithm
- configure TensorFlow and use Jupyter notebooks
- load and explore the MNIST dataset for image classification
- train a deep neural network estimator for image classification
- use an estimator to predict image labels
- describe why deep neural networks don't work well with images
- Define how neural networks work
- recall basics of image classification using neural networks
- define the role of convolutional and pooling layers in a convolutional neural network