justheuristic justheuristic

Course projects

Below are a few ideas on what kinds of projects you can approach for the Practical Deep Learning course @ CS HSE (by Fedor Ratnokov).

The projects in this list are merely examples for you to consider. You may, of course, pick any of them without any alterations, but don't be shy to tailor them to best fulfill your interests or curiosity.

The best possible scenario is when you already have an idea for such project awaiting the opportunity, e.g.:

improving the model in that research you conduct at your department
reproducing that article that you are excited about, but haven't found any reasonable implementation yet

	import theano
	from theano import tensor as T

	trng = T.shared_randomstreams.RandomStreams(1234)

	inner_upd = None
	def OneStep(vsample) :

	def inner(vsample):
	return vsample + trng.normal(size=vsample.shape)

	"""
	## What is it?
	# mostly from http://stackoverflow.com/questions/7323664/python-generator-pre-fetch


	The only parameter here is

	"""

	from lasagne.layers import *
	import theano
	import numpy as np
	def build_resmodule3(inp,filter_size=(3,3)):
	assert(len(inp.output_shape))==4
	n_filters = inp.output_shape[1]
	nn = Conv2DLayer(inp,n_filters,filter_size,pad='same')
	nn = batch_norm(nn) #inserts batchnorm before relu
	nn = ElemwiseSumLayer([nn,inp])
	return nn

	#http://chemspipy.readthedocs.io/en/latest/guide/install.html
	import chemspipy as chpy

	token = "<your token from http://chemspipy.readthedocs.io/en/latest/guide/intro.html#securitytoken>"
	cs = chpy.ChemSpider(token)

	n_samples = 10**5 #amount of molecules to save

	import numpy as np