In my junior year I completed an independent study with Shufan Wang and Prof. Eli Goldwyn on Convolutional Neural Networks for Visual Recognition. We followed an existing Stanford course of the same name. Using an existing library of photographs (CIFAR-10) as our training data, we created a convolutional neural network to classify new photographs. Network properties included a batch normalization layer, dropout, a pooling layer, and some preprocessing. As a “thank you project”, we created the below images. Using neural style transfer, we passed an image of Prof. Goldwyn (left) and allowed the image to adapt to the style of two famous paintings (Starry Night – middle, The Great Wave of Kanagawa – right).

Prof. Eli Goldwyn