Machine Learning

Comparing ResMem and MemNet

In my previous posts about Memorability (see the project link above), I’ve been talking about the performance of my models fairly matter-of-factly. I’ve been comparing their scores on things, reporting them in abstracts, and talking about how one model performs better than another, and why I think that is happening.

ResMem and M3M

In my last post on computer vision and memorability, I looked at an already existing model and started experimenting with variations on that architecture. The most successful attempts were those that use Residual Neural Networks.

ResMem Release

A user-ready version of ResMem is now available on PyPI! The model included in the package is designed to estimate the memorability of an input image but is not intended for feature space analysis.

MemNet: Models for Predicting Image Memorability

Memnet1 was an attempt to build a neural network-based model to predict the memorability of an image. This attempt was carried out by Khosla et al. at the Computer Science and Artificial Intelligence Labs at MIT to moderate success.

Blaseball Ticker Analysis

Introduction In the last week, large swathes of the Internet have been enamored with the simulated sport of blaseball. Blaseball describes itself as “baseball at your mercy, baseball perfected”. I’ve been describing it as “Nightvale-esque simulated baseball with rules decided by a voting system”.

Accelerated Gammatones

Introduction Last winter, I worked on a personal project I call ongaku (from the Japanese for ‘music’). This was an attempt to use manifold learning to create a metric space for music.

Sex, Conspiracy, and Video Games: Urban Legends on the Internet

Introduction Urban Legends, or Contemporary Legends, are a type of folklore popularized by Jan Harold Brunvand in his book: The Vanishing Hitchhiker: American Urban Legends & Their Meanings. Urban Legends

Plurals and ML

Plurals and Machine Learning Using older machine learning models to conjugate English verbs produced rather silly results. These models performed at an acceptable level for many words, but when given nonsense words as an input these models would produce humorous conjugations.

Ongaku

Overview Ongaku is a method for creating playlists programmatically, using only the content of the song alone. It uses gammatone cepstral analysis to create unique matrices to represent each song. A gammatone cepstrum is similar to the more common spectra used for audio analysis.

Fluxx for Robots

Introduction: Fluxx is a mildly popular card game. All things considered, it’s actually fairly contentious. It has a score of 5.7 on Board Game Geek, but it has a serious cult following.