Data Science Workshop: Deep Learning with Python
March 25 @ 2:00 pm – 5:00 pm
Deep Learning (DL) outperforms Machine Learning (ML) in many of the applications related to the Computer Vision (CV) and Natural Language Processing (NLP). One of the biggest advantages of DL over ML is that they can automatically extract the important features from the data. With sufficient data and compute power, DL methods, in particular the supervised learning methods, can achieve the prediction accuracies that were not seen before with any other statistical methods in applications related to CV and NLP.
In this workshop, we will go through the basics of artificial neural networks (ANN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN), and do hands-on training with these DL models to build predictive analytics for image and text data.
Objective of the workshop
- Understand the basics of Artificial Neural Networks (ANN)
- Prepare image and text data suitable for the neural networks
- Learn how to apply various DL models such as ANN, CNN, and RNN
- Improve the accuracy of the model with Hyperparameter Optimization
What is needed? Laptop/Desktop with Internet connection
Duration: 3 hours
Programming Platform: On-line resource or Laptop. Instructions for on-line resources will be given in the workshop.
Prerequisite: Basic laptop usage. Basic knowledge of Python is helpful for doing the hands-on session.
Slides and materials: Will be provided in the workshop
This workshop is hosted by the Office of Advanced Research Computing (OARC), Rutgers University, organized by Bala Desinghu in collaboration with the Eastern Regional Network (ERN) and the New Jersey Big Data Alliance (NJBDA).
Participants are encouraged to attend with campus partners representing a variety of stakeholders for campus research and research computing (e.g., researchers, research computing professionals, students, staff, faculty, and practitioners, etc.).