search
HomeBackend DevelopmentPython TutorialAnalyze the problems of implementing recursive neural networks in Python

Analyze the problems of implementing recursive neural networks in Python

Aug 12, 2017 pm 02:05 PM
pythonNeural Networksrecursion

This article mainly introduces the recursive neural network implemented in Python. It is an article excerpted from github code snippets. It involves operating skills related to Python recursion and mathematical operations. Friends in need can refer to this article

The example describes the recursive neural network implemented in Python. Share it with everyone for your reference, the details are as follows:


# Recurrent Neural Networks
import copy, numpy as np
np.random.seed(0)
# compute sigmoid nonlinearity
def sigmoid(x):
  output = 1/(1+np.exp(-x))
  return output
# convert output of sigmoid function to its derivative
def sigmoid_output_to_derivative(output):
  return output*(1-output)
# training dataset generation
int2binary = {}
binary_dim = 8
largest_number = pow(2,binary_dim)
binary = np.unpackbits(
  np.array([range(largest_number)],dtype=np.uint8).T,axis=1)
for i in range(largest_number):
  int2binary[i] = binary[i]
# input variables
alpha = 0.1
input_dim = 2
hidden_dim = 16
output_dim = 1
# initialize neural network weights
synapse_0 = 2*np.random.random((input_dim,hidden_dim)) - 1
synapse_1 = 2*np.random.random((hidden_dim,output_dim)) - 1
synapse_h = 2*np.random.random((hidden_dim,hidden_dim)) - 1
synapse_0_update = np.zeros_like(synapse_0)
synapse_1_update = np.zeros_like(synapse_1)
synapse_h_update = np.zeros_like(synapse_h)
# training logic
for j in range(10000):
  # generate a simple addition problem (a + b = c)
  a_int = np.random.randint(largest_number/2) # int version
  a = int2binary[a_int] # binary encoding
  b_int = np.random.randint(largest_number/2) # int version
  b = int2binary[b_int] # binary encoding
  # true answer
  c_int = a_int + b_int
  c = int2binary[c_int]
  # where we'll store our best guess (binary encoded)
  d = np.zeros_like(c)
  overallError = 0
  layer_2_deltas = list()
  layer_1_values = list()
  layer_1_values.append(np.zeros(hidden_dim))
  # moving along the positions in the binary encoding
  for position in range(binary_dim):
    # generate input and output
    X = np.array([[a[binary_dim - position - 1],b[binary_dim - position - 1]]])
    y = np.array([[c[binary_dim - position - 1]]]).T
    # hidden layer (input ~+ prev_hidden)
    layer_1 = sigmoid(np.dot(X,synapse_0) + np.dot(layer_1_values[-1],synapse_h))
    # output layer (new binary representation)
    layer_2 = sigmoid(np.dot(layer_1,synapse_1))
    # did we miss?... if so, by how much?
    layer_2_error = y - layer_2
    layer_2_deltas.append((layer_2_error)*sigmoid_output_to_derivative(layer_2))
    overallError += np.abs(layer_2_error[0])
    # decode estimate so we can print(it out)
    d[binary_dim - position - 1] = np.round(layer_2[0][0])
    # store hidden layer so we can use it in the next timestep
    layer_1_values.append(copy.deepcopy(layer_1))
  future_layer_1_delta = np.zeros(hidden_dim)
  for position in range(binary_dim):
    X = np.array([[a[position],b[position]]])
    layer_1 = layer_1_values[-position-1]
    prev_layer_1 = layer_1_values[-position-2]
    # error at output layer
    layer_2_delta = layer_2_deltas[-position-1]
    # error at hidden layer
    layer_1_delta = (future_layer_1_delta.dot(synapse_h.T) + layer_2_delta.dot(synapse_1.T)) * sigmoid_output_to_derivative(layer_1)
    # let's update all our weights so we can try again
    synapse_1_update += np.atleast_2d(layer_1).T.dot(layer_2_delta)
    synapse_h_update += np.atleast_2d(prev_layer_1).T.dot(layer_1_delta)
    synapse_0_update += X.T.dot(layer_1_delta)
    future_layer_1_delta = layer_1_delta
  synapse_0 += synapse_0_update * alpha
  synapse_1 += synapse_1_update * alpha
  synapse_h += synapse_h_update * alpha
  synapse_0_update *= 0
  synapse_1_update *= 0
  synapse_h_update *= 0
  # print(out progress)
  if j % 1000 == 0:
    print("Error:" + str(overallError))
    print("Pred:" + str(d))
    print("True:" + str(c))
    out = 0
    for index,x in enumerate(reversed(d)):
      out += x*pow(2,index)
    print(str(a_int) + " + " + str(b_int) + " = " + str(out))
    print("------------")

Run output:


Error:[ 3.45638663]
Pred:[0 0 0 0 0 0 0 1]
True:[0 1 0 0 0 1 0 1]
9 + 60 = 1
------------
Error:[ 3.63389116]
Pred:[1 1 1 1 1 1 1 1]
True:[0 0 1 1 1 1 1 1]
28 + 35 = 255
------------
Error:[ 3.91366595]
Pred:[0 1 0 0 1 0 0 0]
True:[1 0 1 0 0 0 0 0]
116 + 44 = 72
------------
Error:[ 3.72191702]
Pred:[1 1 0 1 1 1 1 1]
True:[0 1 0 0 1 1 0 1]
4 + 73 = 223
------------
Error:[ 3.5852713]
Pred:[0 0 0 0 1 0 0 0]
True:[0 1 0 1 0 0 1 0]
71 + 11 = 8
------------
Error:[ 2.53352328]
Pred:[1 0 1 0 0 0 1 0]
True:[1 1 0 0 0 0 1 0]
81 + 113 = 162
------------
Error:[ 0.57691441]
Pred:[0 1 0 1 0 0 0 1]
True:[0 1 0 1 0 0 0 1]
81 + 0 = 81
------------
Error:[ 1.42589952]
Pred:[1 0 0 0 0 0 0 1]
True:[1 0 0 0 0 0 0 1]
4 + 125 = 129
------------
Error:[ 0.47477457]
Pred:[0 0 1 1 1 0 0 0]
True:[0 0 1 1 1 0 0 0]
39 + 17 = 56
------------
Error:[ 0.21595037]
Pred:[0 0 0 0 1 1 1 0]
True:[0 0 0 0 1 1 1 0]
11 + 3 = 14
------------

The above is the detailed content of Analyze the problems of implementing recursive neural networks in Python. For more information, please follow other related articles on the PHP Chinese website!

Statement
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
How do you append elements to a Python array?How do you append elements to a Python array?Apr 30, 2025 am 12:19 AM

InPython,youappendelementstoalistusingtheappend()method.1)Useappend()forsingleelements:my_list.append(4).2)Useextend()or =formultipleelements:my_list.extend(another_list)ormy_list =[4,5,6].3)Useinsert()forspecificpositions:my_list.insert(1,5).Beaware

How do you debug shebang-related issues?How do you debug shebang-related issues?Apr 30, 2025 am 12:17 AM

The methods to debug the shebang problem include: 1. Check the shebang line to make sure it is the first line of the script and there are no prefixed spaces; 2. Verify whether the interpreter path is correct; 3. Call the interpreter directly to run the script to isolate the shebang problem; 4. Use strace or trusts to track the system calls; 5. Check the impact of environment variables on shebang.

How do you remove elements from a Python array?How do you remove elements from a Python array?Apr 30, 2025 am 12:16 AM

Pythonlistscanbemanipulatedusingseveralmethodstoremoveelements:1)Theremove()methodremovesthefirstoccurrenceofaspecifiedvalue.2)Thepop()methodremovesandreturnsanelementatagivenindex.3)Thedelstatementcanremoveanitemorslicebyindex.4)Listcomprehensionscr

What data types can be stored in a Python list?What data types can be stored in a Python list?Apr 30, 2025 am 12:07 AM

Pythonlistscanstoreanydatatype,includingintegers,strings,floats,booleans,otherlists,anddictionaries.Thisversatilityallowsformixed-typelists,whichcanbemanagedeffectivelyusingtypechecks,typehints,andspecializedlibrarieslikenumpyforperformance.Documenti

What are some common operations that can be performed on Python lists?What are some common operations that can be performed on Python lists?Apr 30, 2025 am 12:01 AM

Pythonlistssupportnumerousoperations:1)Addingelementswithappend(),extend(),andinsert().2)Removingitemsusingremove(),pop(),andclear().3)Accessingandmodifyingwithindexingandslicing.4)Searchingandsortingwithindex(),sort(),andreverse().5)Advancedoperatio

How do you create multi-dimensional arrays using NumPy?How do you create multi-dimensional arrays using NumPy?Apr 29, 2025 am 12:27 AM

Create multi-dimensional arrays with NumPy can be achieved through the following steps: 1) Use the numpy.array() function to create an array, such as np.array([[1,2,3],[4,5,6]]) to create a 2D array; 2) Use np.zeros(), np.ones(), np.random.random() and other functions to create an array filled with specific values; 3) Understand the shape and size properties of the array to ensure that the length of the sub-array is consistent and avoid errors; 4) Use the np.reshape() function to change the shape of the array; 5) Pay attention to memory usage to ensure that the code is clear and efficient.

Explain the concept of 'broadcasting' in NumPy arrays.Explain the concept of 'broadcasting' in NumPy arrays.Apr 29, 2025 am 12:23 AM

BroadcastinginNumPyisamethodtoperformoperationsonarraysofdifferentshapesbyautomaticallyaligningthem.Itsimplifiescode,enhancesreadability,andboostsperformance.Here'showitworks:1)Smallerarraysarepaddedwithonestomatchdimensions.2)Compatibledimensionsare

Explain how to choose between lists, array.array, and NumPy arrays for data storage.Explain how to choose between lists, array.array, and NumPy arrays for data storage.Apr 29, 2025 am 12:20 AM

ForPythondatastorage,chooselistsforflexibilitywithmixeddatatypes,array.arrayformemory-efficienthomogeneousnumericaldata,andNumPyarraysforadvancednumericalcomputing.Listsareversatilebutlessefficientforlargenumericaldatasets;array.arrayoffersamiddlegro

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

Video Face Swap

Video Face Swap

Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Tools

ZendStudio 13.5.1 Mac

ZendStudio 13.5.1 Mac

Powerful PHP integrated development environment

EditPlus Chinese cracked version

EditPlus Chinese cracked version

Small size, syntax highlighting, does not support code prompt function

PhpStorm Mac version

PhpStorm Mac version

The latest (2018.2.1) professional PHP integrated development tool

Atom editor mac version download

Atom editor mac version download

The most popular open source editor

WebStorm Mac version

WebStorm Mac version

Useful JavaScript development tools