dekhtiar
Mobile-Deep-learning – Mobile Deep Learning Framework by Baidu
Imitation Learning in Tensorflow using Hopper from openAI gym
Named Entity Recognition: Milestone Papers, Models and Technologies
Finding Insights in Scientific Publications
Dataset: 1.6M accidents and traffic flow over 10 years
Python CheatSheet – NumPy
Ask HN: Any Open Deep Learning PostDoctoral Position for Autumn 2018?
I will finish my PhD. in Deep Learning and its applications for the automotive industry in about a year, and I would like to have the time to find a great "next step" and fascinating project.If you hear about any opened PostDoctoral position or R&D position in private companies. Please drop me a message at contact(@)jonathandekhtiar.eu, I will be more than happy to have a talk with you.Have...
An interactive GPU-powered deep dive into 11.6B rows of US shipping data
A Machine Learning Guide – Unsupervised Learning and Related Fields in Practice
Building TensorFlow 1.3.0-rc2 as a standalone project (Raspberry pi 3 included)
Complete Tutorial to Install Deep Learning – Caffe Tensorflow Keras Theano Torch
Show HN: Tech, VentureCapitalist, and Funding Toolkit
Re:Ask HN: How to handle no detection in Deep Learning?
on Tuesday December 06, 2016 @08:47AM (#13114509)
Hello, Thanks a lot for your input.
A discriminator could be a great idea. Any idea on the kind of model efficient for such a task. I'm not sure a CNN is required for such a simple job.
Nowadays, I ouput label + probabilities, however detection threshold can sometimes be around 20% or 70%. I could of course design label-specific threshold, but it doesn't seem to be the correct way.
Or sometimes there is an object in front of me, but not any I know to classify. I would like to be able to detect that this object I don't know.
Concerning entropy, I would definitely give it a shot ! Very nice idea.
Any of you may know a system implementing such behaviour (e.g. I don't detect any object, I don't know this object) ?
Thanks a lot for your help.
Ask HN: How to handle no detection in Deep Learning?
Hello dear friends,I try to develop a Deep Learning Model for my PhD Work that detect a set of objects. And I heavily struggle on one point. How do you handle the fact that none of the "known objects" is detected ? I mean even if I input a black or white image, I still have an output such as "ObjectX: xx%". How to change it for a blank result or "no detection".I obviously can't input millions...
Deepforge: An Open-Source Deep Learning IDE
Noisy Data in Data Mining
Machine Learning for software engineers at producthunt
Re:Ask HN: Open-source requirements management?
on Wednesday October 26, 2016 @05:01AM (#12794954)
Working with Ruby, Javascript, PHP, Python, Bower
Re:Ask HN: Open-source requirements management?
on Wednesday October 26, 2016 @04:59AM (#12794950)
If you mean an open-source project I don't know.
But if you need something free for open-source : https://gemnasium.com/