mbeissinger

Thanks! We want to integrate Tensorflow.js to have the models run in the browser for easy sandbox/experimentation. We loved the visual aspect of Tensorflow Playground and feel a visual graph approach where you can see the output of operations really helps you understand what is happening.

Haha well a GUI for building most computation graphs if you want - at the core you can get down to doing most TensorFlow operations. We even built a GAN using it!

Hey everyone! One of the cofounders of Lobe here - let us know if you have any questions.

No Theano comparison?

Awesome, do you have any demos for the music genre recognition?

Thanks!

Thanks for putting those links up - the Theano documentation has some great tutorials for how to code these in practice.

Nice!

Yes this is really interesting. I haven't read those other papers yet (definitely plan on it now thanks for the links), but Bengio's latest paper on denoising autoencoders from earlier this year (http://arxiv.org/abs/1305.6663) still used the unsupervised pretraining. Also the Theano implementation that I run experiments with uses it as well (but that code could be a year or two old).

Definitely going to be researching this more throughout the year.

I'll definitely check this out if you get a stream going.

Yep the ideas from the 50's have definitely reappeared now we have the compute power and methods to implement them at a large scale. That article gives a nice perspective.

One of the best breakthroughs has been this notion of layer-wise pretraining, which allows the backpropagation algorithm to not get stuck in local minima so easily. It provides a good guess to the starting starting points for the weights. Otherwise, the biggest issue with backpropagation historically has been the diffusion of weights as the layers increase; it is hard to attribute the causality or what portion of the update weighting should be applied to each node since it grows exponentially. This pretraining idea helps against that.

Definitely a solid foundation in linear algebra and statistics (mostly Bayesian) are necessary for understanding how the algorithms work. Check out the wiki portals (http://en.wikipedia.org/wiki/Machine_learning) and (http://en.wikipedia.org/wiki/Artificial_intelligence) for overviews of the most common approaches.

Also, Andrew Ng's coursera course on machine learning is amazing (https://www.coursera.org/course/ml) as well as Norvig and Thrun's Udacity course on AI (https://www.udacity.com/course/cs271)

Odd. I can't replicate on any browser but I don't have OSX. Does it work fine on your other browsers?

Thanks!

Ahh what are you viewing it on?