mat kelcey's repositories
resemblance
trying shingling / resemblance / simhash / sketching to do some data deduping
common-crawl
playing around with the common crawl dataset
cartpoleplusplus
3d cartpole gym env using bullet physics trained from pixels with tensorflow LRPG, DDPG & NAF
ros-mpu6050-node
raspberry pi c++ ROS mpu6050 IMU node
collocations
bigram / trigram analysis of wikipedia; mainly mutual info
wikipediaPhilosophy
do all first links on wikipedia _really_ lead to philosophy?
common-crawl-quick-hacks
common crawl quick hack examples
snli_nn_tf
hacking on the stanford natural language inference (SNLI) corpus (tensorflow)
yahoo_lda_utils
some simple pre/post processing utils for yahoo lda
diy_twitter_client
a simple twitter client that learns what i like to read
neural_prob_lang_model
hacky exploratory variants on NN language models
gardenhose-microslurp
bootstrap scripts for getting a micro ec2 instance piping gardenhose to s3
ros-motorhat-node
raspberry pi c++ ROS wrapper for adafruit motorhat
named-entity-extraction
proof of concept using NLTK for named entity extraction
consistent_hash
afternoon hackery visualising the consistent hash method
mislabelled-training-data
quick experiment on an approach to correct mislabelled data
text-utils
simple c++ corpus munging apps
connected-components
test of iterative python embedded pig
pseudocounts
comparing pseudocount methods
tf-icf-experiment
code for tf/icf experiment (term freq, inverse corpus freq) a system for calculating tf/icf on a stream of data
random-projection
simple random projection experiments
1e6_sentences
simple parsing / embedding utils for the 1e6 sentences dataset
vw_experiments
vowpal experiments