sbos

import numpy as np
from cvxopt import matrix, spmatrix
from cvxopt.solvers import qp
from cvxopt import solvers

class LinearSVM():
	def __init__(self, C):
		self.C = C

	def fit(self, data, labels):

sbos

Снова учитель что-то 
Пытается нам объяснять
Мне случать его неохота
Мне хочется погулять

Я после звонка наплевала
На следующий урок
Сломала окно и сьежала
Слушать тюменский панк-рок

sbos

module HMM

using Distributions

import Distributions.rand
import Distributions.fit

immutable HiddenMarkovModel{TP, K}
    theta::Vector{TP}
    A::Matrix{Float64}

sbos

function write_word2vec(path::AbstractString, vm::VectorModel, dict::Dictionary)
  fout = open(path, "w")
  sense_prob = zeros(T(vm))
  write(fout, "$(V(vm)) $(T(vm)) $(M(vm))\n")
  for v in 1:V(vm)
    write(fout, "$(dict.id2word[v])\n")
    expected_pi!(sense_prob, vm, v)
    for k in 1:T(vm)
      if sense_prob[k] < 1e-3 continue end
      write(fout, "$k $(sense_prob[k]) ")

sbos

==> Using Homebrew-provided fortran compiler.
This may be changed by setting the FC environment variable.
==> Cloning https://github.com/JuliaLang/julia.git
git --git-dir /Library/Caches/Homebrew/julia--git/.git status -s
Updating /Library/Caches/Homebrew/julia--git
git config remote.origin.url https://github.com/JuliaLang/julia.git
git config remote.origin.fetch +refs/heads/master:refs/remotes/origin/master
git fetch origin
git checkout -f master
Already on 'master'

sbos

sbos

import theano as th
import theano.tensor as T
import lasagne
import numpy as np
from theano.tensor.shared_randomstreams import RandomStreams
from lasagne.nonlinearities import tanh
import matplotlib.pyplot as plt
import sys

# change to True and see what happens

sbos

import cgt
import cgt.nn as nn
import numpy as np

batch = 5000

mean = 0.
for i in xrange(batch):
    mean += (cgt.randn() - mean) / (i+1)

sbos

import cgt
import cgt.nn as nn
import numpy as np
from scipy.stats import norm

def gaussian_density(x, mu, sigma):
    return cgt.exp(-cgt.square(x - mu) / 2 / cgt.square(sigma)) \
        / cgt.sqrt(2 * np.pi) / sigma

var_mu = nn.parameter(np.array(0.5))

sbos

import cgt
import cgt.nn as nn
import numpy as np
from scipy.stats import norm

def gaussian_density(x, mu, sigma):
    return cgt.exp(-cgt.square(x - mu) / 2 / cgt.square(sigma)) \
        / cgt.sqrt(2 * np.pi) / sigma

var_mu = nn.parameter(np.array(0.5))