Skip to content

Instantly share code, notes, and snippets.

View khanrc's full-sized avatar

Junbum Cha khanrc

View GitHub Profile
@khanrc
khanrc / gradient_bandits.ipynb
Created January 30, 2018 14:12
Gradient bandit algorithm implementation for 10-armed bandit testbed
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@khanrc
khanrc / pt-mem-leak-test.ipynb
Created January 26, 2018 06:05
DataParallel module leaks memory
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@khanrc
khanrc / transform_performance_test.ipynb
Created November 21, 2017 11:45
Transform performance test
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@khanrc
khanrc / NP-iteration.ipynb
Last active June 23, 2017 02:48
Numpy-iteration-test
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@khanrc
khanrc / regressions.ipynb
Created June 14, 2017 15:26
Linear regression vs. Logistic regresion
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@khanrc
khanrc / BN2.ipynb
Created March 27, 2017 14:37
Why does BN shows bad performance? - V2
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@khanrc
khanrc / bn.ipynb
Created March 27, 2017 13:13
Why does BN shows bad performance?
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@khanrc
khanrc / ae_toy_example.py
Created January 4, 2016 16:15 — forked from hussius/ae_toy_example.py
Toy example of single-layer autoencoder in TensorFlow
import tensorflow as tf
import numpy as np
import math
#import pandas as pd
#import sys
input = np.array([[2.0, 1.0, 1.0, 2.0],
[-2.0, 1.0, -1.0, 2.0],
[0.0, 1.0, 0.0, 2.0],
[0.0, -1.0, 0.0, -2.0],
@khanrc
khanrc / autoencoder.py
Created January 3, 2016 16:19 — forked from k501/autoencoder.py
Tensorflow Auto-Encoder Implementation
""" Deep Auto-Encoder implementation
An auto-encoder works as follows:
Data of dimension k is reduced to a lower dimension j using a matrix multiplication:
softmax(W*x + b) = x'
where W is matrix from R^k --> R^j
A reconstruction matrix W' maps back from R^j --> R^k