Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers the application of Recurrent Neural Networks (RNN) for language detection, where the final hidden activity depends on the whole phrase to predict the language. The instructor demonstrates how to preprocess sentences for language detection using one-hot encoding and joint training with gradient descent. The lecture also discusses the fitting of MNIST data with Convolutional Neural Networks and the use of Tree-Based Methods like Decision Trees and Ensembles. Additionally, it explores the concept of supervised learning through the Big Picture, emphasizing the importance of well-tuned models for optimal performance.
This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.
Watch on Mediaspace