Popularity

2.7

Stable

Activity

0.0

Stable

Stars 212

Watchers 15

Forks 48

Last Commit over 5 years ago

Description

A Handwritten Multilayer Perceptron Classifier

This python implementation is an extension of artifical neural network discussed in Python Machine Learning and Neural networks and Deep learning by extending the ANN to deep neural network & including softmax layers, along with log-likelihood loss function and L1 and L2 regularization techniques.

Code Quality Rank: L4

Programming language: Python

License: MIT License

Tags: Machine Learning Scientific NumPy Classifier Perception Classifier MLP

MLP Classifier alternatives and similar packages

Based on the "Machine Learning" category.
Alternatively, view MLP Classifier alternatives based on common mentions on social networks and blogs.

tensorflow

10.0 10.0 L1 MLP Classifier VS tensorflow

An Open Source Machine Learning Framework for Everyone
Keras

9.9 9.7 L2 MLP Classifier VS Keras

Deep Learning for humans

Delete the most useless function ever: context switching.

Zigi monitors Jira and GitHub updates, pings you when PRs need approval and lets you take fast actions - all directly from Slack! Plus it reduces cycle time by up to 75%.

Promo www.zigi.ai

scikit-learn

9.9 9.9 L3 MLP Classifier VS scikit-learn

scikit-learn: machine learning in Python
gym

9.8 9.5 MLP Classifier VS gym

A toolkit for developing and comparing reinforcement learning algorithms.
xgboost

9.8 9.5 L1 MLP Classifier VS xgboost

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
CNTK

9.6 2.7 L1 MLP Classifier VS CNTK

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
PaddlePaddle

9.6 10.0 L1 MLP Classifier VS PaddlePaddle

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
gensim

9.5 8.5 L3 MLP Classifier VS gensim

Topic Modelling for Humans
Prophet

9.5 6.9 MLP Classifier VS Prophet

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
MLflow

9.4 9.8 MLP Classifier VS MLflow

Open source platform for the machine learning lifecycle
TFLearn

9.3 0.0 L3 MLP Classifier VS TFLearn

Deep learning library featuring a higher-level API for TensorFlow.
MindsDB

9.2 9.9 MLP Classifier VS MindsDB

In-Database Machine Learning
NuPIC

8.9 0.0 L3 MLP Classifier VS NuPIC

Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.
H2O

8.8 9.8 MLP Classifier VS H2O

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
Pyro.ai

8.7 8.1 MLP Classifier VS Pyro.ai

Deep universal probabilistic programming with Python and PyTorch
Surprise

8.4 7.8 L4 MLP Classifier VS Surprise

A Python scikit for building and analyzing recommender systems
srez

8.3 0.0 L5 MLP Classifier VS srez

Image super-resolution through deep learning
Pylearn2

7.9 0.0 L2 MLP Classifier VS Pylearn2

Warning: This project does not have any current developer. See bellow.
LightFM

7.9 5.6 L4 MLP Classifier VS LightFM

A Python implementation of LightFM, a hybrid recommendation algorithm.
PyBrain

7.7 0.0 L4 MLP Classifier VS PyBrain

Another Python Machine Learning Library.
Sacred

7.7 5.2 MLP Classifier VS Sacred

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
skflow

7.6 1.3 L4 MLP Classifier VS skflow

Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning
Clairvoyant

7.3 0.0 L3 MLP Classifier VS Clairvoyant

Software designed to identify and monitor social/historical cues for short term stock movement
python-recsys

6.3 0.0 L4 MLP Classifier VS python-recsys

A python library for implementing a recommender system
Metrics

6.3 0.0 MLP Classifier VS Metrics

Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave
pydeep

6.0 0.0 L3 MLP Classifier VS pydeep

Deep learning in Python
karateclub

5.9 8.5 MLP Classifier VS karateclub

Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
awesome-embedding-models

5.9 0.0 MLP Classifier VS awesome-embedding-models

A curated list of awesome embedding models tutorials, projects and communities.
Crab

5.7 0.0 L2 MLP Classifier VS Crab

Crab is a ﬂexible, fast recommender engine for Python that integrates classic information ﬁltering recommendation algorithms in the world of scientiﬁc Python packages (numpy, scipy, matplotlib).
hebel

5.0 0.0 L2 MLP Classifier VS hebel

GPU-Accelerated Deep Learning Library in Python
seqeval

4.4 0.0 MLP Classifier VS seqeval

A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)
TrueSkill, the video game rating system

4.1 2.2 MLP Classifier VS TrueSkill, the video game rating system

An implementation of the TrueSkill rating system for Python
adaptive

4.0 6.3 MLP Classifier VS adaptive

:chart_with_upwards_trend: Adaptive: parallel active learning of mathematical functions
pdpipe

3.9 8.4 MLP Classifier VS pdpipe

Easy pipelines for pandas DataFrames.
rwa

3.9 0.0 L5 MLP Classifier VS rwa

Machine Learning on Sequential Data Using a Recurrent Weighted Average
SciKit-Learn Laboratory

3.8 4.8 MLP Classifier VS SciKit-Learn Laboratory

SciKit-Learn Laboratory (SKLL) makes it easy to run machine learning experiments.
Feature Forge

3.5 0.0 L4 MLP Classifier VS Feature Forge

A set of tools for creating and testing machine learning features, with a scikit-learn compatible API
brew

3.2 0.0 L4 MLP Classifier VS brew

Multiple Classifier Systems and Ensemble Learning Library in Python.
Data Flow Facilitator for Machine Learning (dffml)

3.2 7.7 MLP Classifier VS Data Flow Facilitator for Machine Learning (dffml)

The easiest way to use Machine Learning. Mix and match underlying ML libraries and data set sources. Generate new datasets or modify existing ones with ease.
bodywork

3.0 9.2 MLP Classifier VS bodywork

ML pipeline orchestration and model deployments on Kubernetes, made really easy.
nptyping

2.9 6.4 MLP Classifier VS nptyping

💡 Type hints for Numpy
vowpal_porpoise

2.4 0.0 L3 MLP Classifier VS vowpal_porpoise

lightweight python wrapper for vowpal wabbit
OptaPy

2.3 8.6 MLP Classifier VS OptaPy

OptaPy is an AI constraint solver for Python to optimize planning and scheduling problems.
redframes

2.1 10.0 MLP Classifier VS redframes

General Purpose Data Manipulation Library
openskill.py

2.1 8.0 MLP Classifier VS openskill.py

A faster, open-license alternative to Microsoft TrueSkill
omega-ml

1.5 10.0 MLP Classifier VS omega-ml

Python analytics made easy - an open source DataOps, MLOps platform for humans
neptune-contrib

1.4 0.0 MLP Classifier VS neptune-contrib

This library is a location of the LegacyLogger for PyTorch Lightning.
tfgraphviz

1.3 0.0 L5 MLP Classifier VS tfgraphviz

A visualization tool to show a TensorFlow's graph like TensorBoard
DeployMe

1.2 10.0 MLP Classifier VS DeployMe

Minimalistic ML-models auto deployment tool
ChaiPy

1.1 5.4 MLP Classifier VS ChaiPy

A developer interface for creating Chat AIs for the Chai app.

* Code Quality Rankings and insights are calculated and provided by Lumnify.
They vary from L1 to L5 with "L5" being the highest.

Do you think we are missing an alternative of MLP Classifier or a related project?

Add another 'Machine Learning' Package

Popular Comparisons

README

MLP Classifier

A Handwritten Multilayer Perceptron Classifier

This python implementation is an extension of artifical neural network discussed in Python Machine Learning and Neural networks and Deep learning by extending the ANN to deep neural network & including softmax layers, along with log-likelihood loss function and L1 and L2 regularization techniques.

Some Basics

An artificial neuron is mathematical function conceived as a model of biological neurons. Each of the nodes in the diagram is a a neuron, which transfer their information to the next layer through transfer function.

The transfer function is a linear combination of the input neurons and a fixed value - bias (threshold in figure). The coefficients of the input neurons are weights.
In the code, bias is a numpy array of size(layers-1) as input layer do not have a bias. The weights, also a numpy array, form a matrix for every two layers in the network.
Activation function is the output of the given neuron.

X: vectorize{(j-1)th layer}

    w = weights[j-1]
    bias = threshold[j-1]
    transfer_function = dot_product(w, X)
    o = activation(transfer_function + bias)

Details

The implementation includes two types of artificial neurons:

Sigmoid Neurons
Softmax Neurons

The loss function associated with Softmax function is the log-likelihood function, while the loss function for Sigmoid function is the the cross-entropy function. The calculus for both loss functions have been discussed within the code.

Further, the two most common regularization techiques - L1 and L2 have been used to prevent overfitting of training data.

Why Softmax?

For zLj in some vector ZL, softmax(zLj) is defined as

The output from the softmax layer can be thought of as a probability distribution.

In many problems it is convenient to be able to interpret the output activation O(j) as the network's estimate of the probability that the correct output is j.

Refer these notes for calculus of softmax function.
Source of MNIST training data-set.