#convolutional-network

What I learned when trying to improve an AI agent in a game using deep learning
▻https://hackernoon.com/what-i-learned-when-trying-to-improve-an-ai-agent-in-a-game-using-deep-l

https://cdn-images-1.medium.com/max/889/1*Ha5GdpPPDfZYwXqPx2jl_A.png

Late 2018 I participated in kaggle’s “Quick, Draw! Doodle Recognition Challenge”.For those of you who are unaware, below is a short description of this game:“Quick, Draw!” was released as an experimental game to educate the public in a playful way about how AI works. The game prompts users to draw an image depicting a certain category, such as ”banana,” “table,” etc.As part of this competition, a subset of more than 1B drawings was released which had 340 labels. The competitors needed to improve the existing AI algorithm which distinguishes whether a user has correctly been able to draw what was asked for. For each test image, the need was to predict the three most probable classes the doodle might belong to.key_id,word9000003627287624,The_Eiffel_Tower airplane (...)

#convolutional-network #deep-learning #kaggle-competition #artificial-intelligence #machine-learning

Traffic Sign Classification
▻https://hackernoon.com/traffic-sign-classification-6e7113d9c4d5?source=rss----3a8144eabfe3---4

https://cdn-images-1.medium.com/max/761/1*GS__aSMeD-pPTYKXbOCb_g.png

Having just finished the semester at NYU, I thought I’d share the results of one of the more interesting homework assignments that I had. As the title suggests, this will be another post about the traffic sign classification competition found at ▻http://benchmark.ini.rub.de/.For some background, I am currently studying for my master’s degree at NYU. Like many of the other students there, I jumped at the chance to take the computer vision class taught by the renowned professor Rob Fergus.Cool, but what makes this assignment more interesting than any other assignment from any other professor? This homework assignment was given in the form of a #kaggle competition. The higher your rank on the private leaderboard the higher your grade.For those that don’t know what the private leaderboard is on (...)

#image-classification #convolutional-network #machine-learning #computer-vision

Multi-GPU training with Brain Builder and #tensorflow
▻https://hackernoon.com/multi-gpu-training-with-brain-builder-and-tensorflow-3b7aba2eb84b?source

https://cdn-images-1.medium.com/proxy/1*5H4PvayHZT6AZyVFeFprtA.png

Yes, building AI is hard! Every step from data annotation, training and deployment comes with its own set of challenges. This blog post will try to deal with the first two of those:Data AnnotationTrainingOver the past few years at Neurala, we have been developing highly efficient AI systems deployed in millions of consumer devices as of today! And in this process, we developed a lot of tools to simplify our workflow. We have finally decided to bridge the AI skills gap by making some of our tools public. One of the tools, Brain Builder deals with the first of the aforementioned issues: Data Annotation.Brain Builder is an AI-assisted annotation tool that fits seamlessly into commonly used frameworks like TensorFlow and Caffe. This post will walk you through the steps you’d need to (...)

#convolutional-network #deep-learning #machine-learning #data-science