{"version":"1.0","type":"rich","title":"A notebook describing how to use t-SNE to visualize a neural network learn representations","description":"This notebook demonstrates how a convolutional neural network learns to recognize handwritten digits from the MNIST database by visualizing its internal representations with t-SNE. It shows the network’s high-level feature layer (h_fc2) projected into two dimensions at various training stages, revealing clusters that correspond to digit classes. The code trains a LeNet-style model using TensorFlow, then applies sklearn.manifold.TSNE to the learned activations. Matplotlib renders the resulting scatter plots, with each point colored by its true label, illustrating how representations become more separable as training progresses.","provider_name":"VizHub AI Studio","provider_url":"https://next.vizhub.com","html":"<iframe src=\"https://next.vizhub.com/viz/gist-7e5dd9f040f4d3121858232d854b0123?mode=embed\" width=\"960\" height=\"500\" scrolling=\"no\" frameborder=\"1\"></iframe>","width":960,"height":500,"cache_age":3600}