mycat
Joined 9 years ago
Karma
186
Submissions
60
Member since
Jul 7
Recent submissions
Comment · 9 years ago
Comment · 9 years ago
How does it compare with, Spiking Neural Network?
Both use vectors (but in different way) to encode more information
Comment · 9 years ago
How about DBN? It is also a generative model but why now rarely used?
ML researchers following trends, like doing end-to-end CNN for whatever problems, and using this LSTM and that GRU and that latest architectures; in similar fashion like web devs picking and dropping javascript frameworks.
Comment · 9 years ago
For me, this book's first chapters explained nicely about ML, MAP and Bayesian using real computer vision problems. The author included helpful visual aids (gaussian plots, contour plots, filters output, etc)
http://www.computervisionmodels.com
This is a rather unusual book where it gives primer on probabilistic method that is actually applicable in non computer vision problems. It is Bayesian heavy and rarely touches neural networks; the book is released in 2012, the year deep learning boom started.
Comment · 9 years ago
This. Until your side hustle income is roughly the same as your day job, don't quit.
Comment · 9 years ago
Can elaborate more on that?
Currently I know Python and am using Django.
I am too lazy to learn Ruby. Is it worth it to learn Ruby just to use Rails?
Comment · 9 years ago
How does it compare with Sony's e ink tablet with stylus? Seems too similar except it is made by startup
Comment · 9 years ago
BeOS has extreme task scheduling to give smooth UI, for example if you run too many programs at once, BeOS network connection has noticeable stutter even if your UI seems slick enough
Comment · 9 years ago
I thought recently they made e ink monitor. But not laptop though.. More like a giant tablet
http://www.dasung.com/english/
Comment · 9 years ago
Bayesian machine learning for neural networks. Currently learning PyMC3 and Edward.
Stop before you feel full.