Kaixhin

# Run MATLAB file and output to file
matlab -nodisplay -r <function> [<params>...] > <file>
# Email output file once done
mutt -s "Results" <email> < <file>

Kaixhin

require 'cunn'
local cudnn = require 'cudnn'

local X = torch.rand(32, 3, 24, 24):cuda()
local Y = torch.ones(32):cuda()

local net = nn.Sequential()
net:add(cudnn.SpatialConvolution(3, 8, 5, 5))
net:add(nn.View(8*20*20))
net:add(nn.Linear(8*20*20, 10))

Kaixhin

Weekly Maintenance

Windows 8.1

• CCleaner
• Check Disk
• System Image Backup

OS X 10.9 Mavericks

• CCleaner
• Verify Disk

Kaixhin

--[[
--   Gaussian Processes for Dummies
--   https://katbailey.github.io/post/gaussian-processes-for-dummies/
--   Note 1: The Cholesky decomposition requires positive-definite matrices, hence the addition of a small value to the diagonal (prevents zeros along the diagonal)
--   Note 2: This can also be thought of as adding a little noise to the observations
--]]

local gnuplot = require 'gnuplot'

-- Test data

Kaixhin

--[[
-- Using Perlin Noise to Generate 2D Terrain and Water
-- http://gpfault.net/posts/perlin-noise.txt.html
--]]

local image = require 'image'

-- Fade function
local fade = function(t)
  -- Provides continuous higher order derivatives for smoothness (this specifically is in the class of sigmoid functions)

Kaixhin

--[[
--   Element-Research Torch RNN Tutorial for recurrent neural nets : let's predict time series with a laptop GPU
--   https://christopher5106.github.io/deep/learning/2016/07/14/element-research-torch-rnn-tutorial.html
--]]

--[[
--   Part 1
--]]

require 'rnn'

Kaixhin

import torch


def cast(cuda):
  if cuda:
    return lambda x: x.cuda()
  else:
    return lambda x: x

Kaixhin

--[[
--   Random walks down Wall Street, Stochastic Processes in Python
--   http://www.turingfinance.com/random-walks-down-wall-street-stochastic-processes-in-python/
--]]

local gnuplot = require 'gnuplot'

local model_parameters = {
  all_s0 = 1000, -- Starting asset value
  all_time = 800, -- Amount of time to simulate for

Kaixhin

"""
Introduction to Monte Carlo Tree Search
http://jeffbradberry.com/posts/2015/09/intro-to-monte-carlo-tree-search/
"""

from copy import deepcopy
import datetime
from math import log, sqrt
from random import choice

Kaixhin

import os
import torch
from torch import nn, optim
from torch.nn import functional as F
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
from torchvision.utils import save_image


class Encoder(nn.Module):