Markus Beissinger

[...] into bag-of-words or n-grams as features. Choosing the correct feature representation of input data, or feature engineering, is a way that people can bring prior knowledge of a domain to increase [...]

[...] process as with RBMs: One disadvantage of auto-encoders is that they can easily memorize the training data - i.e. find the model parameters that map every input seen to a perfect reconstruction with [...]

[...] , adventures, random thoughts, etc. This blog’s main purpose, however, is going to be my thesis research in deep learning as well as some thoughts on entrepreneurship. Hopefully we can have a [...]

[...] you a layman understanding of what deep learning actually is so you can follow some of my thesis research this year as well as mentally filter out news articles that sensationalize these buzzwords. [...]

[...] an orthogonal basis for the dh orthogonal directions of greatest variance in the input training data x. The result is dh features that make representation layer h that are decorrelated. ( [...]

[...] as latent random variables. In this case, you care about the probability distribution of the input data x and the hidden latent random variables h that describe the input data in the joint [...]

[...] window being open. Here are all the commands and the order I used to set up Theano: sudo apt-get update update the default packages sudo apt-get -y dist-upgrade upgrade screen -S “theano” create a [...]

[...] models: restricted boltzmann machine (RBM) A Boltzmann machine is a network of symmetrically-coupled binary random variables or units. This means that it is a fully-connected, undirected graph. This [...]

Theano is an amazing Python package for deep learning that can utilize NVIDIA's CUDA toolkit to run on the gpu. The gpu is orders of magnitude faster [...]

[...] hierarchical representation of the input data to create useful features for traditional machine learning algorithms. Each layer in the hierarchy learns a more abstract and complex feature of the [...]