yusugomori

# -*- coding: utf-8 -*-

import sys
import numpy

numpy.seterr(all='ignore')


'''

yusugomori

/*
 * SdA.cpp (Stacked Denoising Autoencoders)
 *
 * @author  yusugomori (http://yusugomori.com)
 * @usage   $ g++ SdA.cpp
 *
 */

#include <iostream>
#include <math.h>

yusugomori

#!/usr/bin/env python
# -*- coding: utf-8 -*-

'''
 Deep Belief Nets (DBN)

 References :
   - Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle: Greedy Layer-Wise
   Training of Deep Networks, Advances in Neural Information Processing
   Systems 19, 2007

yusugomori

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
 Restricted Boltzmann Machine (RBM)

 References :
   - Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle: Greedy Layer-Wise
   Training of Deep Networks, Advances in Neural Information Processing
   Systems 19, 2007

yusugomori

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
 Denoising Autoencoders (dA)

 References :
   - P. Vincent, H. Larochelle, Y. Bengio, P.A. Manzagol: Extracting and
   Composing Robust Features with Denoising Autoencoders, ICML'08, 1096-1103,
   2008

yusugomori

#!/usr/bin/env python
# -*- coding: utf-8 -*-

'''
 Logistic Regression
 
 References :
    - Jason Rennie: Logistic Regression,
   http://qwone.com/~jason/writing/lr.pdf
 

yusugomori

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
 Stacked Denoising Autoencoders (SdA)

 References :
   - P. Vincent, H. Larochelle, Y. Bengio, P.A. Manzagol: Extracting and
   Composing Robust Features with Denoising Autoencoders, ICML' 08, 1096-1103,
   2008

yusugomori

from keras.optimizers import Optimizer
from keras.legacy import interfaces
from keras import backend as K
import tensorflow as tf


class Adabound(Optimizer):
    def __init__(self, lr=0.001,
                 beta_1=0.9, beta_2=0.999,
                 gamma=0.001,

yusugomori

import os
import subprocess
import random
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optimizers
from torch.autograd import Variable

yusugomori

// $ scalac DBN.scala
// $ scala DBN


import scala.util.Random
import scala.math


class RBM(val N: Int, val n_visible: Int, val n_hidden: Int,
          _W: Array[Array[Double]]=null, _hbias: Array[Double]=null, _vbias: Array[Double]=null,