What my deep model doesn’t know…

@tachyeonz : I come from the Cambridge machine learning group. More than once I heard people referring to us as “the most Bayesian machine learning group in the world”. I mean, we do work with probabilistic models and uncertainty on a daily basis.

Read More

Connect On:
Twitter :@tachyeonz

Advertisements

What my deep model doesn’t know…

@tachyeonz : I come from the Cambridge machine learning group. More than once I heard people referring to us as “the most Bayesian machine learning group in the world”. I mean, we do work with probabilistic models and uncertainty on a daily basis.

More

Tags : caffe, cambridge, conv.js, geoffrey hinton, karpathy, machine learning, models, uncertainity, yann le cun, z

Published On:January 03, 2017 at 04:20PM

Connect On:
Facebook : /tachyeonz
Twitter :@tachyeonz

NIPS 2016 Review, Day 2

@tachyeonz : Why good morning again, fellow machine learners. It’s another day at NIPS, and what a grueling experience. The sessions ran from 9am to 9pm last night, and I was there for most of it! (Check out my NIPS 2016 Review, Day 1 for the low-down on yesterday’s action.) Ok, let’s get crackin’.

More

Tags : gans, generative adversarial, gradient descent, kyle cranmer, m, models, nips2016, pgm, probabilistic graphical, sgd, stochastic

Published On:December 26, 2016 at 05:13PM

Connect On:
Facebook : /tachyeonz
Twitter :@tachyeonz

Machine Learning Performance Improvement Cheat Sheet

@tachyeonz : The most valuable part of machine learning is predictive modeling. This is the development of models that are trained on historical data and make predictions on new data.

Click here to read more

Tags : #algorithms, #machinelearning, #models, #optimization, #statistics, #techniques, m

Published On:November 23, 2016 at 01:08AM

Connect On:
Facebook : /tachyeonz
Twitter :@tachyeonz