William Wolf cavaunpeu

Random variables

A variable: a thing that can take on a bunch of different values.

Which part is random?

Formally, a random variable deterministically maps elements of one set to another.
Once we have the value in the first set, i.e. the "measurement" of "what kind of a Monday it is," we know the value in the second, i.e. the color of shirt I will wear.

	Will Wolf is inviting you to a scheduled Zoom meeting.

	Topic: Will's 31st Birthday Party!
	Time: May 31, 2020 11:00 AM Eastern Time (US and Canada)

	Join Zoom Meeting
	https://asapp.zoom.us/j/98245285251?pwd=aVN2ZWZXRjVPU1A0TkhZcmRRNWpjQT09

	Meeting ID: 982 4528 5251
	Password: 076822

	# Ensure that p(~ \| z_k) = 1, i.e. the probability of jumping from a given state to any other state is 1
	self._A = nn.Parameter(A)
	_A_triu = self._A.triu().detach()
	A_triu = []
	for i, row in enumerate(_A_triu):
	nz = row[row.nonzero().view(-1)]
	if i == 0:
	probs = F.softmax(nz, dim=-1)
	else:
	probs = nz.exp() * (1 - torch.stack(A_triu)[:, i].sum()) / nz.exp().sum()

	# Your init script
	#
	# Atom will evaluate this file each time a new window is opened. It is run
	# after packages are loaded/activated and after the previous editor state
	# has been restored.
	#
	# An example hack to log to the console when each text editor is saved.
	#
	# atom.workspace.observeTextEditors (editor) ->
	# editor.onDidSave ->

	# halp?

	def foo(x, y):
	return f(x, y) + g(x, y)
	g_foo = grad(foo, argnum=1)

	bar = a + b
	g_bar = tf.gradients(bar, var_list)

	# g_bar == g_foo(x, y) ... TRUE

	GENES = 'ATGC'


	def generate_next_kmers(kmer, k=3, genes=GENES):
	if k == 0:
	yield kmer
	else:
	for gene in genes:
	yield from generate_next_kmers(kmer + gene, k=k-1)

	def generate_batch(batch_size, num_skips, skip_window):
	global data_index
	assert batch_size % num_skips == 0
	assert num_skips <= 2 * skip_window
	batch = np.ndarray(shape=(batch_size), dtype=np.int32)
	labels = np.ndarray(shape=(batch_size, 1), dtype=np.int32)
	span = 2 * skip_window + 1 # [ skip_window target skip_window ]
	buffer = collections.deque(maxlen=span)
	for _ in range(span):
	buffer.append(data[data_index])