Probabilistic Deep Network
This post explains a trick which allows us to convert neural network outputs into probabilities, with no cost to performance,
Read moreRobotics & Computer Vision Engineer, PhD
This post explains a trick which allows us to convert neural network outputs into probabilities, with no cost to performance,
Read moreThis post presents an interesting summary of the RSS 2016 Workshop Here you can fine official page and description of the
Read moreTiny-CNN is an header-only, dependency-free deep learning framework for C++11. Just include tiny_cnn.h and write your model in C++. There is
Read moreNormal estimation in point clouds is a crucial first step for numerous algorithms, from surface reconstruction and scene understanding to
Read moreHow about asking your robot to make a complete laundry cycle?…PR2 seems almost there. See more on this page.
Read moreIn this nice post, LSTMs are described to have more control than typical RNNs over what they remember. In general,
Read moreFrom Eugenio Curlurciello’s blog, Professor at Purdue University, you can find here a post about the the history of neural network design
Read moreHere you can find a fantastic post on reinforcement learning by Andrej Karpathy. The Author explains how it is possible
Read moreFrom the webpage of the project “This paper presents a novel probabilistic foundation for volumetric 3-d reconstruction. We formulate the problem as
Read moreIn this work from Georgia Tech, researchers have developed a control algorithm that allows small-scale autonomous cars to drive autonomously around
Read moreGoogle revealed the TPU (Tensor Processing Unit), a custom ASIC designed and built specifically for machine learning applications.
Read moreMovidius (innovative Irish chip maker) has just created the world’s first deep learning USB stick. Entitled the Fathom Neural Compute Stick,
Read moreCheck this page… and have fun playing with neural networks.
Read moreA new work of Lepetit and Fua about learning invariant feature trasform http://arxiv.org/abs/1603.09114
Read more