• In this post we introduce how to use TensorFlow.js by demonstrating how it was used in the simple project Neural Titanic. In this project, we show how to visualize the evolution of the predictions of a single layer neural network as it is being trained on the tabular Titanic Dataset for the task of binary classification of

  • Given as the April talk to Danbury.IO: A full stack developer born in the dark ages of the LAMP stack discusses his transition to a modern JavaScript centric stack for creating robust web applications: MongoDB Express Vue Node ( MEVN ). This talk gives an overview of the MEVN stack, but focuses on the

  • We recently gave a talk on Semantic Segmentation to Danbury AI. One of the first fundamental problems of computer vision was the classification of images — where we are given a matrix of pixel data and we must each pixel a categorical class label. When we can classify images, in our computer vision applications we can

  • Presentation given for the January meeting of Danbury AI. Recurrent Neural Networks ( RNN ) are a special configuration of Neural Networks for processing sequential data. In this talk we discuss the ideas behind RNNs and several fascinating applications of RNNs which allow us to produce samples of high perceptual similarity to training set data. “Much

  • Presentation given for the December meeting of Danbury AI. Art has always been cherished as the most expressive and human production. The idea that a computer, a logical machine, can create the most quintessential human objects is preposterous to some. As anyone that has engaged in the artistic process will tell you, a lot of