|
Abstract:
|
Recent advances in computer hardware and algorithms have enabled proliferation of the use of deep learning models in many practical applications. Popular open source frameworks for deep learning include Keras, TensorFlow, Caffe and PyTorch. IBM Watson Studio provides several ways to build deep learning models using those frameworks, from Python Jupyter notebooks and RStudio to the graphical interface of the Neural Network Modeler. The latter allows graphical construction of deep learning models with automatic Python code creation. This workshop will first provide an introduction to the theory of traditional neural networks, then discuss convolutional and recurrent networks and their applications. Deep learning examples using the Keras library will be shown in Jupyter notebooks, RStudio, and the Neural network modeler. Attendees can get some hands-on experience with those tools. Model deployment strategies and the model interchange format ONNX will be discussed. Finally, we will examine open source packages AIFairness360 and Adversarial Robustness Toolkit developed in collaboration with IBM Research. Participants should be familiar with fundamentals of statistical modeling, and will gain a basic understanding of some popular deep learning methods including possible applications and available tools.
|
