Depths of Deep Learning

About this blog post series The wild success of Deep Neural Network (DNN) models in a variety of domains has created considerable excitement in the machine learning community. Despite this success, a deep understanding of why DNNs perform so well, and whether their performance is somehow brittle, has been lacking. Two recent developments hold promise in shedding light on the behavior of DNNs, and could point the way to improving deep learning models [Read More]

With forestry when editing inline math equations we need to carefully watch for the rich-text editor inserting extra backslashes, munging underscores, etc. Inline math with double-backslash-parens: \(E = mc^2 - a_i - \sum_i y_i\) works just fine. Weirdly, inline math within dollar signs $ E = mc^2 - a_i + \sum_i y_i $ also works but the fonts are subtly different. Normal display math enclosed in double-dollar signs: $$ E = \sum_i m_i c_i^2 $$ display math with equation aligned (note we don't need the double-dollar sign, since the align environment triggers MathJax. [Read More]

With forestry when editing inline math equations we need to carefully watch for the rich-text editor inserting extra backslashes, munging underscores, etc. Inline math with double-backslash-parens: \(E = mc^2 - a_i - \sum_i y_i\) works just fine. Weirdly, inline math within dollar signs $ E = mc^2 - a_i + \sum_i y_i $ also works but the fonts are subtly different. Normal display math enclosed in double-dollar signs: $$ E = \sum_i m_i c_i^2 $$ display math with equation aligned (note we don't need the double-dollar sign, since the align environment triggers MathJax. [Read More]