TensorFlow: open-source library for machine intelligence

Post by hmehta » Tue, Nov 10, 2015, 12:56 AM UTC

w_t_payne wrote: post #173

elcritch wrote: post #171

Earlier quoted context omitted.

Nice, lol, hope TensorFlow didn't scoop any of your ideas too. ;) Overall, it's exciting to see data-flow paradigms gain popularity. What kind of dataflow approach are you most interested in? I've been shifting my approach to work within existing systems. One things I've been doing is abusing the intent of web-components and DOM events to create data visualization tools. Recently my team and I decided to focus down a…

Nothing too serious ... mostly to glue embedded machine vision system components together in a simulation environment.

Post by benanne » Tue, Nov 10, 2015, 1:07 AM UTC

obstbraende wrote: post #106

benanne wrote: post #102

Earlier quoted context omitted.

Why wouldn't this work in Theano? >>> import theano >>> import theano.tensor as T >>> state = theano.shared(1.0) >>> states = [] >>> for step in range(10): >>> state = state + state >>> states.append(state) >>> >>> f = theano.function([], states) >>> f() [array(2.0), array(4.0), array(8.0), array(16.0), array(32.0), array(64.0), array(128.0), array(256.0), array(512.0), array(1024.0)]

Thanks! When I tried this before, I thought compilation was stuck in an infinite loop and gave up after about a minute. But you're right, it works. Though on my machine, this took two and a half minutes to compile (ten times as long as compiling a small convnet). For 10 recurrence steps, that's weird, right? And the TensorFlow thing above runs instantly.

Post by tianlins » Tue, Nov 10, 2015, 1:18 AM UTC

mtw wrote: post #40

kragen wrote: post #8

This is really significant. At this moment in history, the growth of computer power has made a bunch of important signal-processing and statistical tasks just feasible, so we are seeing things like self-driving cars, superhuman image recognition, and so on. But it's been very difficult to take advantage of the available computational power, because it's in the form of GPUs and clusters. TensorFlow is a library design…

What about Torch or Theano which allow you to use multiple GPUs and clusters? they also have a wide array of libraries which allows you to extend capabilities (itorch etc.). torch is also very fast, most parts written in C so I don't know if Tensorflow would be really that fast compared to existing librairies. One thing find I found interesting is the ability to use the software you designed in research directly in p…

Post by orasis » Tue, Nov 10, 2015, 1:22 AM UTC

Zephyr314 wrote: post #160

kragen wrote: post #8

This is really significant. At this moment in history, the growth of computer power has made a bunch of important signal-processing and statistical tasks just feasible, so we are seeing things like self-driving cars, superhuman image recognition, and so on. But it's been very difficult to take advantage of the available computational power, because it's in the form of GPUs and clusters. TensorFlow is a library design…

Depending on how long it takes to "evaluate the goodness of a solution" techniques like multi-start gradient decent can rapidly become intractable though, especially in higher dimensions. There are a handful of open source libraries out there that try to tackle this time consuming and expensive black box optimization problem from a more Bayesian approach [1] [2]. There's also a YC company to do this as a service (ful…

Post by Swizec » Tue, Nov 10, 2015, 1:37 AM UTC

infinii wrote: post #184

sytelus wrote: post #153

Earlier quoted context omitted.

Why is alphabetical order great? It just only means that people with last names starting with z will get penalized every single time because of choosing wrong parents! I would think randomized order would be chosen - especially if you were mathematician.

"Choose" parents with a surname starting with A then.