Arthur Juliani awjuliani
awjuliani
/ rl-tutorial-1.ipynb
Last active
February 2, 2020 05:04
Reinforcement Learning Tutorial 1 (Two-armed bandit problem)
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
awjuliani
/ pg-pong.py
Created
June 5, 2016 02:12
— forked from karpathy/pg-pong.py
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """ | |
| import numpy as np | |
| import cPickle as pickle | |
| import gym | |
| # hyperparameters | |
| H = 200 # number of hidden layer neurons | |
| batch_size = 10 # every how many episodes to do a param update? | |
| learning_rate = 1e-4 | |
| gamma = 0.99 # discount factor for reward |
awjuliani
/ Deep Layer Visualization.ipynb
Last active
January 28, 2021 10:18
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
awjuliani
/ cryptArithmetic.m
Created
April 5, 2016 22:28
Matlab script to solve basic cryptarithmetic problems.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| clear ; close all; clc | |
| %Get input for three terms | |
| prompt = 'First three letter term? '; | |
| x1 = input(prompt, 's'); | |
| prompt = 'Second three letter term? '; | |
| x2 = input(prompt, 's'); | |
| prompt = 'Four letter answer? '; | |
| y = input(prompt, 's'); |
awjuliani
/ RNN-TF.ipynb
Created
March 16, 2016 19:30
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
awjuliani
/ 3D t-SNE export.py
Created
March 3, 2016 23:25
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import os | |
| newpath = r'./csvs' | |
| if not os.path.exists(newpath): | |
| os.makedirs(newpath) | |
| iters = 0 | |
| for i in finalRepresentations: | |
| tsne = TSNE(perplexity=50, n_components=3, init='pca', n_iter=5000) | |
| plot_only = 2000 | |
| lowDWeights = tsne.fit_transform(i[0:plot_only,:]) |
awjuliani
/ t-SNE Tutorial.ipynb
Created
March 2, 2016 18:13
A notebook describing how to use t-SNE to visualize a neural network learn representations
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
awjuliani
/ softmax.ipynb
Last active
September 14, 2021 20:52
A simple ipython notebook that walks through the creation of a softmax regression model using MNIST dataset.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
NewerOlder