xavierdcruz0

import numpy as np
import itertools

# update rule for neuron x1
def update_1((a, b, c)):
    test = c-b+2
    if (test > 0):
        new = 1
    elif (test == 0):
        new = a

xavierdcruz0

file_path = expanduser('results/pickles/image-mlp.prm')

layers = []
layers.append(DataLayer(nout=100))
layers.append(FCLayer(nout=10, activation=RectLin()))
layers.append(FCLayer(nout=3, activation=RectLin()))
layers.append(FCLayer(nout=3, activation=Logistic()))
layers.append(CostLayer(cost=CrossEntropy()))

backend = gen_backend(rng_seed=0)

xavierdcruz0

import logging

logging.basicConfig(level=40)
logger = logging.getLogger()

from neon.backends import gen_backend
from neon.layers import FCLayer, DataLayer, CostLayer
from neon.models import MLP
from neon.transforms import RectLin, Logistic, CrossEntropy
from neon.experiments import FitPredictErrorExperiment

xavierdcruz0

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Deep learning experiments on artificial generated signals\n",
    "\n",
    "First we need to setup the environment and import all the necessary stuff."
   ]

xavierdcruz0

import logging

logging.basicConfig(level=40)
logger = logging.getLogger()

from neon.backends import gen_backend
from neon.layers import FCLayer, DataLayer, CostLayer
from neon.models import MLP
from neon.models import DBN
from neon.transforms import RectLin, Logistic, CrossEntropy

xavierdcruz0

package com.AwesomeSoft;

import org.canova.api.records.reader.RecordReader;
import org.canova.api.split.FileSplit;
import org.canova.image.recordreader.ImageRecordReader;
import org.deeplearning4j.datasets.canova.RecordReaderDataSetIterator;
import org.deeplearning4j.datasets.iterator.DataSetIterator;
import org.deeplearning4j.nn.conf.MultiLayerConfiguration;
import org.deeplearning4j.nn.conf.NeuralNetConfiguration;
import org.deeplearning4j.nn.conf.layers.OutputLayer;