Comments for iMonad.com http://imonad.com/blog Software engineering, Functional programming, Haskell Sun, 23 Nov 2008 14:00:32 +0000 http://wordpress.org/?v=2.6.3 Comment on Restricted Boltzmann Machine - Short Tutorial by zoo http://imonad.com/blog/2008/10/restricted-boltzmann-machine/#comment-54 zoo Fri, 10 Oct 2008 10:41:49 +0000 http://imonad.com/blog/?p=65#comment-54 I appreciate you suggestions and will update the article. I appreciate you suggestions and will update the article.

]]> Comment on Restricted Boltzmann Machine - Short Tutorial by chef-ele http://imonad.com/blog/2008/10/restricted-boltzmann-machine/#comment-53 chef-ele Thu, 09 Oct 2008 16:44:31 +0000 http://imonad.com/blog/?p=65#comment-53 Here's some nit-picky editorial comments that might help clarify the text (feel free to ignore these, though!): In the section that starts with "The algorithm as a whole is:", you do not have an explicit step that updates the weights & biases. The needed formulas are in a section above, where you wrote that "CD = 0 - n" and "W’ = W + alpha*CD". Copying those two lines into the list of steps for the algorithm would make the algorithm a bit clearer, I think. Next, on the diagrams, it might be helpful to explicitly label the blue nodes as visible nodes & the brown nodes as hidden nodes. Also, when you say, "Si.Sj is just a multiplication of current activation (state) of neuron I and neuron J" it might be slightly clearer to explicitly say that Si is the state of a visible neuron, and Sj is the state of a hidden neuron. This becomes more obvious later on, but at that point in the text one might think Si & Sj could be the states of two different neurons in the same layer, which they're not. Here’s some nit-picky editorial comments that might help clarify the text (feel free to ignore these, though!):

In the section that starts with “The algorithm as a whole is:”, you do not have an explicit step that updates the weights & biases. The needed formulas are in a section above, where you wrote that “CD = 0 - n” and “W’ = W + alpha*CD”. Copying those two lines into the list of steps for the algorithm would make the algorithm a bit clearer, I think.

Next, on the diagrams, it might be helpful to explicitly label the blue nodes as visible nodes & the brown nodes as hidden nodes.

Also, when you say, “Si.Sj is just a multiplication of current activation (state) of neuron I and neuron J” it might be slightly clearer to explicitly say that Si is the state of a visible neuron, and Sj is the state of a hidden neuron. This becomes more obvious later on, but at that point in the text one might think Si & Sj could be the states of two different neurons in the same layer, which they’re not.

]]>