Machine Learning
Machine Learning is an application of artificial intelligence (AI).
It provides the ability to learn and improve from experience.
Good part is that it does not need to be explicitly programmed to improve learning.
Term ML/Machine Learning was coined in 1959 by American pioneer named Arthur Samuel at IBM.
It is evolved from the study of pattern recognition and artificial intelligence. ML explores the study and construction of algorithms that can learn from and make predictions of data by making decisions through building a model from sample inputs.
Tom M. Mitchell quote ML as "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E."
Primary aim of this is to allow the computers learn automatically without human intervention and take the most appropriate action on the basis of learning.
Have a look: https://github.com/collections/machine-learning
Keep Practicing, Keep Learning and Keep Smiling :)
It provides the ability to learn and improve from experience.
Good part is that it does not need to be explicitly programmed to improve learning.
ML or Machine Learning focuses on the development of computer programs that can access data and use the same data to predict or learn for itself.
Term ML/Machine Learning was coined in 1959 by American pioneer named Arthur Samuel at IBM.
It is evolved from the study of pattern recognition and artificial intelligence. ML explores the study and construction of algorithms that can learn from and make predictions of data by making decisions through building a model from sample inputs.
Tom M. Mitchell quote ML as "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E."
Primary aim of this is to allow the computers learn automatically without human intervention and take the most appropriate action on the basis of learning.
Some of the ML methods are as:
- Supervised ML Algorithms:
Past experience data is used to predict the next move of future.
It can also compare its output with the correct, intended output and find errors in order to modify the model
- Unsupervised ML Algorithms:
Information used to train is neither classified nor labeled. It studies how systems can infer a function to describe a hidden structure from unlabeled data.
The system does not figure out the correct output but helps to find out the hidden structures from unlabeled data.
- Semi-supervised ML Algorithms:
It is in between supervised and unsupervised algo, so it uses both the labeled and unlabeled data for the system to get the result near to future/ prediction.
It is designed in a way so that small amount of data is provided from the set of labeled and large amount of data from the unlabeled data.
It supports system to constantly improve the learning accuracy.
- Reinforcement ML Algorithms:
It interacts with its environment by producing actions and discovers errors or rewards. Trial and error search and delayed reward are the most relevant characteristics of it.ML enables analysis of huge data and prediction system can be made out of the past results.
It helps system to automatically determine the ideal behavior within a specific context in order to maximize its performance.
Some of the approaches are as:
- Decision tree learning
- Association rule learning
- Artificial neural networks
- Deep Learning
- Inductive Logic Programming
- Support Vector Machines
- Clustering
- Basyesian Networks
- Reinforcement Learning
- Representation Learning
- Similiarity and metric Learning
- Sparse dictionary Learning
- Genetic Algorithms
- Rule-based Machine Learning
- Learning Classifier Systems
Free and open-source software:
- CNTK
- Deeplearning4j
- dlib
- ELKI
- GNU Octave
- H2O
- Mahout
- Mallet
- MEPX
- mlpy
- MLPACK
- MOA (Massive Online Analysis)
- MXNet
- ND4J: ND arrays for Java
- NuPIC
- OpenAI Gym
- OpenAI Universe
- OpenNN
- Orange
- R
- scikit-learn
- Shogun
- TensorFlow
- Torch
- Yooreeka
- Weka
Have a look: https://github.com/collections/machine-learning
Keep Practicing, Keep Learning and Keep Smiling :)
