Neuralnetwork - Basic Multilayer Perceptron Neural Network for deep learning

Last update: Nov 01, 2022

Related tags

Deep Learning neuralnetwork

Overview

Neural Network

Just a basic Neural Network module

Usage Example

Importing Module

from neuralnetwork import NeuralNetwork
import numpy as np

Initiating

Initiate NeuralNetwork class with parameters:

NeuralNetwork(input_nodes: int, hidden_nodes: int, output_nodes: int)

model = NeuralNetwork(3, 2, 1)

Set 3 inputs nodes, 2 hidden nodes, and 1 output node

Training

For this example, we want to train our machine with data below. Basically, our expected output are just the first number of inputs.

[0, 0, 1] = 0
[0, 1, 0] = 0
[1, 0, 1] = 1
[1, 1, 0] = 1

Set training data for inputs and target outputs, and train with train(inputs, targets) method through some number of iterations, until you statisfied. This example: 20000 iterations

# Training data inputs
inputs = np.array([
    [0, 0, 1],
    [0, 1, 0],
    [1, 0, 1],
    [1, 1, 0],
])
# Training data target outputs
targets = np.array([[0, 0, 1, 1]]).T

# iterate to train
for i in range(20000):
    model.train(inputs, targets)

Predicting

After a training above, now we test our machine to predict an output for given input.

Example: [0, 1, 1] should produce 0, because 0 is the first number.

# Question
question = np.array([[0, 1, 1 ]])
print("Question:")
print(question)
# Prediction
prediction = model.think(question)
print("Prediction:")
print(prediction)

Result

This is the terminal result

Training Data
[[0 0 1]
 [0 1 0]
 [1 0 1]
 [1 1 0]]
Training Target
[[0]
 [0]
 [1]
 [1]]
...
target output after training
[[0.00344796]
 [0.00344796]
 [0.99647399]
 [0.99647399]]
---------------
Question:
[[0 1 1]]
Prediction:
[[0.00332841]]

From [0, 1, 1] input, we predict: 0.003 (almost nearly zero)

Woohoo! You just build your machine learning

How we know our accurracy?

The "target output after training" above should match nearly the "training target" actual data.

Full example is located in examples/basic.py file

Project Structure

/
├── neuralnetwork.py    # core module
├── pyproject.toml
├── README.rst
├── examples             # containing examples of usage
│   ├── basic.py        # basic usage example
│   └── __init__.py
└── tests
    ├── __init__.py
    └── *.py

Visualizer for neural network, deep learning, and machine learning models

Netron is a viewer for neural network, deep learning and machine learning models. Netron supports ONNX (.onnx, .pb, .pbtxt), Keras (.h5, .keras), Tens

21k Jan 6, 2023

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

The Neural Process Family This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CN

892 Dec 28, 2022

PPLNN is a Primitive Library for Neural Network is a high-performance deep-learning inference engine for efficient AI inferencing

943 Jan 7, 2023

TJU Deep Learning & Neural Network

Deep_Learning & Neural_Network_Lab 实验环境 Python 3.9 Anaconda3(官网下载或清华镜像都行) PyTorch 1.10.1(安装代码如下) conda install pytorch torchvision torchaudio cudatool

1 Jan 19, 2022

Analyzing basic network responses to novel classes

novelty-detection Analyzing how AlexNet responds to novel classes with varying degrees of similarity to pretrained classes from ImageNet. If you find

34 Oct 2, 2022

Pytorch Implementation of Adversarial Deep Network Embedding for Cross-Network Node Classification

Pytorch Implementation of Adversarial Deep Network Embedding for Cross-Network Node Classification (ACDNE) This is a pytorch implementation of the Adv

8 Oct 13, 2022

Scripts of Machine Learning Algorithms from Scratch. Implementations of machine learning models and algorithms using nothing but NumPy with a focus on accessibility. Aims to cover everything from basic to advance.

Algo-ScriptML Python implementations of some of the fundamental Machine Learning models and algorithms from scratch. The goal of this project is not t

81 Nov 26, 2022

Neural-net-from-scratch - A simple Neural Network from scratch in Python using the Pymathrix library

A Simple Neural Network from scratch A Simple Neural Network from scratch in Pyt

2 Jan 7, 2022

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.

Object Pose Estimation Demo This tutorial will go through the steps necessary to perform pose estimation with a UR3 robotic arm in Unity. You’ll gain

187 Dec 24, 2022

Neuralnetwork - Basic Multilayer Perceptron Neural Network for deep learning

Related tags

Overview

Neural Network

Usage Example

Importing Module

Initiating

Training

Predicting

Result

Project Structure

You might also like...

Visualizer for neural network, deep learning, and machine learning models

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

PPLNN is a Primitive Library for Neural Network is a high-performance deep-learning inference engine for efficient AI inferencing

TJU Deep Learning & Neural Network

Analyzing basic network responses to novel classes

Pytorch Implementation of Adversarial Deep Network Embedding for Cross-Network Node Classification

Scripts of Machine Learning Algorithms from Scratch. Implementations of machine learning models and algorithms using nothing but NumPy with a focus on accessibility. Aims to cover everything from basic to advance.

Neural-net-from-scratch - A simple Neural Network from scratch in Python using the Pymathrix library

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.

Releases(v0.1.0)

v0.1.0(Jan 24, 2022)

Owner

andreecy

AoT is a system for automatically generating off-target test harness by using build information.

3rd Place Solution of the Traffic4Cast Core Challenge @ NeurIPS 2021

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

Degree-Quant: Quantization-Aware Training for Graph Neural Networks.

A library for using chemistry in your applications

SmoothGrad implementation in PyTorch

An easy-to-use app to visualise attentions of various VQA models.

Magisk module to enable hidden features on Android 12 Developer Preview 1.

“Robust Lightweight Facial Expression Recognition Network with Label Distribution Training”, AAAI 2021.

Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences forImage-Text Retrieval

Anonymize BLM Protest Images

Supporting code for "Autoregressive neural-network wavefunctions for ab initio quantum chemistry".

Wordplay, an artificial Intelligence based crossword puzzle solver.

Datasets, Transforms and Models specific to Computer Vision

Code for "Typilus: Neural Type Hints" PLDI 2020

A fast poisson image editing implementation that can utilize multi-core CPU or GPU to handle a high-resolution image input.

PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)

Neural Caption Generator with Attention

This repository is the official implementation of the Hybrid Self-Attention NEAT algorithm.

TAPEX: Table Pre-training via Learning a Neural SQL Executor