∅
@natural_origin
462
subscribers
478
photos
23
videos
36
files
941
links
Download Telegram
Join
∅
462 subscribers
∅
∅
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness Abstract: Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes.…
∅
https://youtu.be/xP5-iIeKXE8
YouTube
Life in life
A video of Conway's Game of Life, emulated in Conway's Game of Life.
The Life pattern is the OTCA Metapixel: http://www.conwaylife.com/wiki/OTCA_metapixel - for more information, see http://otcametapixel.blogspot.com.au/
The life simulator used is Golly…
∅
∅
∅
∅
https://erikmcclure.com/blog/factorio-is-best-interview-we-have/
Erik McClure
Factorio Is The Best Technical Interview We Have
There’s been a lot of hand-wringing over The Technical Interview lately. Many people realize that inverting a binary tree on a whiteboard has basically zero correlation to whether or not someone is actually a good software developer. The most effective programming…
∅
∅
https://www.scientificamerican.com/article/bad-news-for-the-highly-intelligent/
Scientific American
Bad News for the Highly Intelligent
Superior IQs are associated with mental and physical disorders, research suggests
∅
∅
https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.PassiveAggressiveRegressor.html
∅
∅
∅
∅
∅
∅
∅
∅
https://sh-tsang.medium.com/review-addernet-do-we-really-need-multiplications-in-deep-learning-image-classification-b72851ddb255
Medium
Review — AdderNet: Do We Really Need Multiplications in Deep Learning? (Image Classification)
Using Addition Instead of Multiplication for Convolution, Lower Latency Than the Conventional CNN
∅
https://www.wetheweb.org/post/cancel-we-the-web
∅
∅
