-
Backprop by Hand and CNNs on MNISTHand-computing one step of backpropagation, then iterating on CNN architectures in MATLAB until giving up and switching to Keras.
5 min -
Fractals for Image Classification Feature ExtractionMapping images to a 1D signal with a Hilbert curve, compressing with wavelets, and classifying with SVMs on MNIST and Fashion-MNIST.
5 min -
BiLSTM-CNN-CRF for Sequence Labeling: A TutorialA PyTorch reproduction of the End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF paper for the ICML 2018 reproducibility workshop.
9 min -
Deep Learning Methods for Quotable TextExploring what makes a sentence memorable using deep learning, achieving significant improvements over traditional linguistic feature approaches.
9 min
Back