- Classifying Images with Convolutional Networks: Get an overview of the course. Perform image classification using pretrained networks. Use transfer learning to train customized classification networks.
- Interpreting Network Behavior: Gain insight into how a network is operating by visualizing image data as it passes through the network. Apply this technique to different kinds of images.
- Creating Networks: Build convolutional networks from scratch. Understand how information is passed between network layers and how different types of layers work.
- Training Networks: Understand how training algorithms work. Set training options to monitor and control training.
- Improving Performance: Choose and implement modifications to training algorithm options, network architecture, or training data to improve network performance.
- Spectrogram Classification Project:
- Performing Regression: Create convolutional networks that can predict continuous numeric responses.
- Using Deep Learning for Computer Vision: Train networks to locate and label specific objects within images.
- Classifying Sequence Data with Recurrent Networks: Build and train networks to perform classification on ordered sequences of data, such as time series or sensor data.
- Classifying Categorical Sequences: Use recurrent networks to classify sequences of categorical data, such as text.
- Generating Sequences of Output: Use recurrent networks to create sequences of predictions.
- Sequence Classification Project:
- Conclusion: Learn next steps and give feedback on the course.
Overview
Syllabus
- Course Overview
- Review - Deep Learning Onramp
- Extracting and Visualizing Activations
- Visualizing Network Predictions
- Review - Interpreting Network Behavior
- Training from Scratch
- Course Example - Landcover Classification
- Creating Network Architectures
- Understanding Neural Networks
- Convolutional Layers
- Viewing Filters
- Review - Creating Networks
- Understanding Network Training
- Monitoring Training Progress
- Validation
- Review - Training Networks
- Troubleshooting Methods
- Training Options
- Experiment Manager
- Augmented Datastores
- Review - Improving Performance
- Representing Signal Data as Images
- Project - Classify Spectrograms
- What is Regression
- Transfer Learning for Regression
- Evaluating a Regression Network
- Review - Performing Regression
- Computer Vision Applications
- Ground Truth
- YOLO Object Detectors
- Evaluating Object Detectors
- Review - Deep Learning for Computer Vision
- Long Short-Term Memory Networks
- Course Example - Classify Musical Instruments
- Structuring Sequence Data
- Sequence Classification
- Improving LSTM Performance
- Review - Classifying Sequence Data with Recurrent Networks
- Course Example - Author Identification
- Categorical Sequences
- Classify Text Data
- Review - Classifying Categorical Sequences
- Sequence-to-Sequence Classification
- Investigate Sequence Scores
- Sequence Forecasting
- Review - Generating Sequences of Output
- Project - Robot Navigation
- Summary
- Additional Resources
- Survey
Taught by
Renee Bach
