Our friends at Startup.ml are hosting a Deep learning workshop.
This full-day event will help you understand how to use the state-of-the-art techniques in deep learning in multiple applications.
A special 25% discount only available until Oct 5 using the code "insiders" http://conf.startup.ml
François Chollet will be reconstructing "Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks" paper using Keras-based RNNs to answer reading comprehension questions. This is an ambitious attempt to make AI-level conversations possible.
For the object detection task, we will implement the recent state-of-the-art paper "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks." This paper exemplifies the modularity of deep learning by combining aspects of separate convolutional neural network (CNN) models. Markus Beissinger will lead this workshop using OpenDeep.
Arjun Bansal will show us Recurrent Neural Networks that can be used to generate and analyze text, and build Convolutional Autoencoders that can be used to generate images and to localize objects.
Looking forward to a great conference!