Deep learning is a prominent topic in the AI field. it has been around for a long time. It has received much attention because it has made breakthroughs beyond human capabilities in computer vision (ComputerVision) and AlphaGO. Since the last investigation, attention to deep learning has increased significantly. Deep learning is a prominent topic in the AI field. it has been around for a long time. It has received much attention because it has made breakthroughs beyond human capabilities in Computer Vision and Alpha GO. Since the last investigation, attention to deep learning has increased significantly.
This is what Google Trends show us:
1. Scikit-learn (recommended)
Scikit-learn is a Python module built based on Scipy for machine learning. it features a variety of classifications. regression and clustering algorithms include support vector machines, logical regression, and naive Bayes classifier, random Forest, Gradient Boosting, clustering algorithm and DBSCAN. Python numerical and scientific libraries Numpy and Scipy are also designed.
2. Keras (deep learning)
Keras is a deep learning framework based on Theano. it is designed based on Torch and written in Python. it is a highly modular neural network library that supports GPU and CPU.
3. Lasagne (deep learning)
It is not just a delicious Italian dish, but also a deep learning library with similar features as Keras, but it is somewhat different in design.
4. Pylearn2
Pylearn is a Theano-based library program that simplifies machine learning research. It encapsulates many common models and training algorithms for deep learning and artificial intelligence research into a single experimental package, such as random gradient descent.
5. NuPIC
NuPIC is a machine intelligence platform using HTM learning algorithms. HTM is a precise calculation method of cortex. The core of HTM is the time-based continuous learning algorithm and the storage and Revocation Time-space mode. NuPIC is suitable for various problems, especially for detecting abnormal and predicted stream data sources.
6. Nilearn
Nilearn is a Python module that enables quick statistics and learning of neural image data. It uses the scikit-learn toolbox in the Python language and some applications for predictive modeling, classification, decoding, and connectivity analysis for multivariate statistics.
7. PyBrain
Pybrain is short for Python-based reinforcement learning, artificial intelligence, and neural network libraries. Its goal is to provide flexible, easy-to-use and powerful machine learning algorithms and compare your algorithms in a variety of predefined environments.
8. Pattern
Pattern is a network mining module in Python. It provides tools for data mining, natural language processing, network analysis, and machine learning. It supports vector space model, clustering, support vector machine and perception machine, and uses KNN classification for classification.
9. Fuel
Fuel provides data for your machine learning model. He has an interface that shares datasets such as MNIST, CIFAR-10 (image dataset), and Google's One Billion Words (text. You can use it to replace your data in many ways.
10. Bob
Bob is a free signal processing and machine learning tool. Its Toolbox is written in Python and C ++ languages. it is designed to be more efficient and reduce development time. it is a processing image tool, audio and video processing, machine learning, and pattern recognition.
11. Skdata
Skdata is a database program for machine learning and statistics data sets. This module provides standard Python for the use of popular computer vision and natural language datasets for toy problems.
12. MILK
MILK is a machine learning toolkit in Python. It is mainly used in many possible classifications such as SVMS, K-NN, random forest, decision tree supervised classification. It also performs feature selection. These classifiers can be combined in many aspects to form different classification systems, such as unsupervised learning, closely related gold propagation, and K-means clustering supported by MILK.
13. IEPY
IEPY is an open-source information extraction tool focusing on link extraction. It mainly targets users who need to extract information from large datasets and scientists who want to try new algorithms.
14. Quepy
Quepy is a Python framework for querying in the database query language by changing natural language problems. It can be simply defined as different types of problems in natural language and database queries. Therefore, you can build your own system that uses natural language to access your database without coding.
Quepy now supports Sparql and MQL query languages. It is planned to extend to other database query languages.
15. Hebel
Hebel is a library program for deep learning of neural networks in Python. it uses PyCUDA to accelerate GPU and CUDA. It is the most important tool of the neural network model type and can provide activation functions for some different movable functions, such as power, nesjrov power, signal loss and stop methods.
16. mlxtend
It is a library program composed of useful tools and extensions of daily data science tasks.
17. nolearn
This package contains a large number of utility modules that can help you complete machine learning tasks. A large number of modules work with scikit-learn, and others are usually more useful.
18. Ramp
Ramp is a library program that develops a solution for accelerating prototype design in machine learning in Python. He is a lightweight pandas-based machine learning plug-in framework that provides machine learning and statistical tools (such as scikit-learn and rpy2) in Python) ramp provides a simple declarative syntax exploration function to implement algorithms and transformations quickly and effectively.
19. Feature Forge
These tools use APIs compatible with scikit-learn to create and test machine learning functions.
This library provides a set of tools that can be used by many machine learning programs. When you use the scikit-learn tool, you will feel a lot of help. (Although this only works when you have different algorithms .)
20. REP
REP is an environment provided by command data mobile driver in a harmonious and renewable manner.
It has a unified classifier packaging to provide a variety of operations, such as TMVA, Sklearn, XGBoost, uBoost, and so on. In addition, the classifier can be trained in a group in a parallel manner. It also provides an interactive plot.
21. Python learning machine samples
Collect simple software built with Amazon Machine Learning.
22. Python-ELM
This is an implementation of an extreme learning machine based on scikit-learn in Python.
23. gensim
Theme model python implementation
Scalable statistical semantics
Analyze plain-text documents for semantic structure
Retrieve semantically similar documents