Data Science Austria

DeepFool — A simple and accurate method to fool deep Neural Networks.

An Adversarial Attack ArunavaBlockedUnblockFollowFollowing May 17 Fig 1. Its not a fish, its a bird 🙂 [Confidences shown are the values of logits and not passed through softmax] Summary of the paperDeepFool: A Simple and Accurate Method to Fool Deep Neural Networksby Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Pascal FrossardLink to the paper: https://arxiv.org/pdf/1511.04599.pdf … Read moreDeepFool — A simple and accurate method to fool deep Neural Networks.

LSTM Autoencoder for Extreme Rare Event Classification in Keras

Here we will learn the details of data preparation for LSTM models, and build an LSTM Autoencoder for rare-event classification. This post is a continuation of my previous post Extreme Rare Event Classification using Autoencoders. In the previous post, we talked about the challenges in an extremely rare event data … Read moreLSTM Autoencoder for Extreme Rare Event Classification in Keras

The story and Future of ImageAI – One year Anniversary

Global reach, case studies and future versions of ImageAI It is with utmost excitement that I write this piece, not only because the ImageAI project has made incredible impact since it’s launch on the 22nd of March 2018, but because of the innovations that will be made possible by the project … Read moreThe story and Future of ImageAI – One year Anniversary