313e120f25crossEntropy chart for now
Mahdi Dibaiee
2016-09-16 14:36:42 +0430
6def5f6197draw chart using simple options
Mahdi Dibaiee
2016-09-16 14:16:14 +0430
0d43814448fix(word2vec): simple example of word2vec
Mahdi Dibaiee
2016-09-16 14:03:15 +0430
d4ac90bbd5rm(sin): remove sin example fix(ignoreBiases): was ignoring nodes, lol fix(w2v): better logging and implementation
Mahdi Dibaiee
2016-09-16 13:31:23 +0430
6b9cb1fa3erelu: run notmnist using relu activation and draw the chart [wip] word2vec: work in progress implementation of word2vec
Mahdi Dibaiee
2016-09-13 09:49:44 +0430
f379f208dbfix(crossEntropy): implement crossEntropy' to be used in output layer fix(softmax'): softmax was not correct
Mahdi Dibaiee
2016-09-10 17:43:45 +0430
891f48a2d0feat(topten): top-ten classification with evenly distrubuted data
Mahdi Dibaiee
2016-08-21 00:59:42 +0430
b2888417bbfix(cleanText): remove unnecessary spaces fix(run): use 1 - prior for alpha, no need for smoothing feat(cleanText): turn all text to lowercase
Mahdi Dibaiee
2016-08-09 16:04:57 +0430
eebf5e0222feat(verbose): print more information using -v or --verbose flags
Mahdi Dibaiee
2016-08-08 12:35:26 +0430
099c25e166feat(stopwords): removeWords and removeStopwords functions as pre-processors feat(confidence, WIP): calculate confidence of each classification
Mahdi Dibaiee
2016-08-08 10:02:26 +0430
ea1f05f001fix(naivebayes): fix the algorithm to make it actually work feat(cleanDocuments): preprocess documents, use stemming and stopword elimination for better accuracy
Mahdi Dibaiee
2016-08-05 23:54:36 +0430
3cf0625794fix(precision): little bug in implementation
Mahdi Dibaiee
2016-07-30 16:52:34 +0430
76e7e7faeffix(recall, precision): little bug in calculations feat(fmeasure): calculate fmeasure using recall and precision
Mahdi Dibaiee
2016-07-29 22:09:30 +0430
812717522erefactor(&&&): use &&& instead of the arrow function
Mahdi Dibaiee
2016-07-29 18:20:35 +0430
b5b4629318feat(results): accuracy, recall and precision functions used to calculate measures fix: read data from another repository
Mahdi Dibaiee
2016-07-29 17:55:59 +0430
26eb4531fafeat(naivebayes): implement NaiveBayes algorithm feat(example): a document classifier using NaiveBayes over reuters data
Mahdi Dibaiee
2016-07-29 16:16:44 +0430
493a20eb0afeat(crossEntropy): crossEntropy cost function
Mahdi Dibaiee
2016-07-24 10:48:04 +0430
49606406d1fix(run): I had written logistic' wrong, that's what happens when you write code while sleepy
Mahdi Dibaiee
2016-07-20 12:06:19 +0430