ASL Recognition with Deep Learning
Build a convolutional neural network to classify images of letters from American Sign Language.Start Project
9 Tasks1,500 XP
Loved by learners at thousands of companies
American Sign Language (ASL) is the primary language used by many deaf individuals in North America, and it is also used by hard-of-hearing and hearing individuals. The language is as rich as spoken languages and employs signs made with the hand, along with facial gestures and bodily postures.
In this project, you will train a convolutional neural network to classify images of ASL letters. After loading, examining, and preprocessing the data, you will train the network and test its performance.
- 1American Sign Language (ASL)
- 2Visualize the training data
- 3Examine the dataset
- 4One-hot encode the data
- 5Define the model
- 6Compile the model
- 7Train the model
- 8Test the model
- 9Visualize mistakes
Alexis CookSee More
Machine Learning Educator at Kaggle
Alexis is an AI educator with a background in mathematics. She formerly worked as a Curriculum Lead at Udacity, where she built content in deep learning, including applications to computer vision, natural language processing, and reinforcement learning.