Computing the optimal stop placement for transit
Like many people, I take the bus to work most days. My commute isn’t actually that far (about 3 miles), but I am incredibly lazy, and the bus lets me catch up on the magazines that would otherwise be...
View Articlesocial security is backwards
Don’t get me wrong by the title: as a society we should definitely support our elderly. But what I want to consider here is: given a fixed amount of money to spend on a given citizen, when is the...
View Articlecoding like it’s 1979
It’s old news, but I just discovered Cathode and it’s pretty much made my day week. There’s something so charming about the feel of analog devices and Cathode comes very close to the real thing. Or at...
View ArticleDeep Neural Networks for YouTube Recommendations
https://research.google.com/pubs/archive/45530.pdf This paper describes the system used for YouTube’s personalized recommendations. It’s a somewhat typical “experience” paper, but notable in a few...
View ArticleReview: Named Entity Recognition with Bidirectional LSTM-CNNs
http://arxiv.org/pdf/1511.08308v5 Combining LSTMs with CNNs seems to a popular theme these days. It makes sense: CNNs can be very fast to train for language recognition tasks, and are certainly easier...
View ArticleA Deep Relevance Matching Model for Ad-hoc Retrieval
A Deep Relevance Matching Model for Ad-hoc Retrieval Synopsis: A lot of models have been proposed for using deep-learning for comparing text, but they don’t tend to work for the specific task of...
View ArticleHolographic Embeddings of Knowledge Graphs
http://arxiv.org/pdf/1510.04935v2.pdf Review: I really liked this paper. The approach is refreshingly uncomplicated. The use of circular correlation is well-argued, and the experimental results speak...
View Articlepup is great!
I definitely do more HTML scraping than is healthy for a person. And inevitably, I end up spending more time doing the scraping than I would have spent doing some copy-pasting. So of course I’m...
View ArticleReview: Energy Based Generative Adversarial Networks
Link: https://arxiv.org/pdf/1609.03126v2.pdf TLDR Energy based framework makes for more robust models An interesting bit: their model internally learns an auto-encoder. But: it’s allowed to...
View ArticleReview: Order Matters: Sequence to Sequence for Sets
We now have good tooling for handling sequential inputs (e.g. RNNs). But what about variable sized inputs that have no explicit ordering? We can use a sequential model, but in what order do we feed...
View Article