1. Failure to reimplement: on the future-proofing of research papers

    Failing to reimplement a paper

  2. A Unified Architecture for Natural Language Processing

    Review of Collobert & Weston (2008)

  3. Generating DNA barcdes with Numpy

    A tour through the process of optimizing slow code

  4. Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference

    After a long hiatus, I’m going to write about another paper I read recently, that is changing the way I think about using deep networks for biological sequence problems.

    Background

    Anyone that’s working in applied machine learning these days is familiar with the idea of convolutional neural networks …

  5. Basset: multi-task convolutional networks for predicting regions chromatin from sequence

    I've been reading a few papers recently that each involve training a deep network that takes input directly from sequence and predicts some aspect of chromatin. Deep Bind predicts protein-DNA binding, and DeepSEA predicts the effect of SNPs on chromatin state. The most recent paper, and the one I find …

Page 1 / 2 »