Tags » Neural Networks

Orbica: Using machine vision in GIS

Last week I had the opportunity to sit down with Orbica CEO’s Kurt Janssen and data scientist  Sagar Soni.

Kurt has worked in the Geographic Information Systems (GIS) industry for more than 14-years. 647 more words

Deep Learning

Activation Functions

The notion of an activation function is best understood by first conceptualizing the inspiration behind it — i.e. the impulse activation threshold that must be crossed in order for a neuron to ‘fire’ ( 427 more words


Higgs Hacking

by Giles Strong

A few days before I returned from CERN at the beginning of the month, I attended a talk on the upcoming TrackML challenge… 2,692 more words

ESR Experience

Understanding Long Short-Term Memory Networks (LSTMs)

Remember how in the previous article we’ve said that we can predict text and make speech recognition work so well with Recurrent Neural Networks? The truth is that all the big accomplishments that we assigned to RNNs in the previous article are actually achieved using special kind of RNNs – Long Short-Terms Memory Units (LSTMs). 1,213 more words

FPGA Weekly Meetings - W VIII

This Tuesday:

  • We’ll review the implementation of the LSTM neural network on Xilinx Zynq MPSoC is SDSoC
  • We’ll start a discussion on the organization of the III FPGA Symposium
FPGA Weekly

Lecture 2: Word Vector Representations: word2vec


This relates to broader category a word will belong to. For eg red is a color and car is a motor_vehicle.

They also show… 300 more words

Neural Networks in 10 Lines of code


This blog post is for those who learn by doing. I had actually started a blog post series on Deeplearning but then realized that it could get pretty boring and intimidating if it consists of lots of theory before the fun coding part starts hence I have decided to put this post so you can learn by doing. 747 more words