Kaixhin

I supervise undergraduate/postgraduate/UROP projects as part of BICV. The PI, Dr Anil Bharath, has a nice set of FAQs for prospective research students, which should give you an idea of what our group specialises in. My topic of research is deep reinforcement learning, which is less focused on computer vision and more on general machine learning or even artificial intelligence. Note that I only supervise students at Imperial College London, so please do not contact me about supervision otherwise.

I expect students to be a) highly motivated and b) technically proficient.

a) Projects that I supervise revolve around cutting-edge research, and specifically deep learning. Projects can, and have in the past, relied on research released during the course of the project. Some parts of machine learning can be found in optional modules in bioengineering courses, but (modern) deep learning is currently not taught at Imperial (as far as I am aware). I usually give crash

Kaixhin

# Collection of LSTM cells (including forget gates)
# https://en.wikipedia.org/w/index.php?title=Long_short-term_memory&oldid=784163987

import torch
from torch import nn
from torch.nn import Parameter
from torch.nn import functional as F
from torch.nn.modules.utils import _pair
from torch.autograd import Variable

Kaixhin

"""
The Annotated Transformer
http://nlp.seas.harvard.edu/2018/04/03/attention.html
Note: Only includes basic example, not real world example or multi-GPU training
"""


import numpy as np
import torch
import torch.nn as nn

Kaixhin

from matplotlib import pyplot as plt
from mpl_toolkits import mplot3d

def scatter(X, Y, c=None, ax=None):
  ax = plt.axes() if ax is None else ax
  ax.scatter(X.numpy(), Y.numpy(), c=None if c is None else c.numpy())
  return ax

def contour(X, Y, Z, levels=None, ax=None):
  ax = plt.axes() if ax is None else ax

Kaixhin

Description

I collect the first volumes (and first volumes only) of various manga series (in English) in new condition.

Wishlist

I have an Amazon wishlist, but volumes from other series that I do not have are also welcome. New books only please.

Library

Kaixhin

Probability notation

Note: Great refresher/glossary on probability/statistics and related topics here

Notation	Definition
X	Random variable
P(X)	Probability distribution over random variable X
X ~ P(X)	Random variable X follows (~) the probability distribution P(X) *

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):

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

--[[
--   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

import torch


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