![• Web search
• Computational biology
• Finance
• E-commerce
• Space exploration
• Robotics
• Information extraction
• Social networks
• Debugging
• [Your favorite area]
Applications](https://image.slidesharecdn.com/machinelearningalgorithm-230616044521-05025d3c/85/machine-learning-algorithm-pptx-16-320.jpg)
machine learning algorithm.pptx
- 1. A Review on Machine Learning Algorithms Presented By: Sushree Sasmita Dash ITER, S’O’A Deemed to be University, Bhubaneswar
- 2. Introduction • Machine Learning (ML) is the subset of Artificial Intelligence that provides computer systems the ability to simulate human intelligence. • It enables computer systems for searching and identifying hidden information or patterns, without being programmed explicitly, when exposed to new data sets.
- 3. • The success of machine learning system depends on the algorithms. • Researchers have developed many machine learning algorithms. • Practitioner are mostly concerned with choosing the most appropriate algorithm for the problem at hand • This requires some a priori knowledge – data distribution, prior probabilities, complexity of the problem, the physics of the underlying phenomenon, etc. • However, given some a priori information, certain classifiers may better MATCH the characteristics of certain type of problems. • The main challenge of the practitioner is then, to identify the correct match between the problem and the classifier! • So, here we are focusing on different types of machine learning algorithms. Motivation
- 4. Types of Learning Machine Learning Supervised Naive Bayes Decision Tree Support Vector Machine Unsupervised Principal Component Analysis K_Means Semi_supervised Self Training Transductive SVM Generative Models multitasking Reinforced Ensemble Bagging Boosting Instance Based K_nearest neighbour Neural network Supervised Unsupervised Reinforced
- 5. In supervised learning, the machine is trained or taught using some well-labeled data. Supervised Learning
- 6. • Decision Tree. Mainly groups the attributes into different classes by sorting the values associated with the attributes . • Naïve Bayes. These algorithms are probabilistic algorithms based on applying Bayes' theorem with strong (naïve) independence assumptions between the features. • Support Vector Machine (SVM). A Support Vector Machine (SVM) is a discriminative classifier formally defined by a separating hyper plane. In other words, given labelled training data (supervised learning), the algorithm outputs an optimal hyper plane which categorizes new examples. Types of Supervised Learning
- 7. In unsupervised learning, the algorithms are able to group unsorted information without any labeled data, only considering the similarities and differences present between those data. Unsupervised Learning
- 8. • K-Means Algorithm. The objective of this algorithm is to cluster data points that are similar in nature and detect the underlying patterns. For this objective to be achieved, K- means clusters the dataset into a fixed (K) number of clusters. • Principal Component Analysis (PCA). It is a statistical procedure that uses an orthogonal transformation to reduce the number of variables and clusters them into a manageable group called components or factors. Types of unsupervised Learning
- 9. • Here, the algorithm works upon both unlabeled and few labeled data. • At first, the algorithm clusters similar types of data using the unsupervised learning algorithm and then the rest will be labeled by taking the help of previously taken a few numbers of labeled data. Semi-Supervised Learning
- 10. • Reinforcement learning is the problem faced by an agent that learns behaviour through trial-and-error interactions with a dynamic environment. Reinforcement Learning is learning how to act in order to maximize a numerical reward. Reinforcement Learning
- 11. • Multitask learning is used to make the performance better for other learners. When this algorithm is applied to a particular task the whole procedure for solving the problem is remembered by it. Thereafter, it solves other similar types of problems by using these steps. Multitask Learning
- 12. • Here multiple learners such as classifiers or experts solve a particular problem together. • Types are boosting, that often considers homogeneous weak learners, learns them sequentially in a very adaptative way (a base model depends on the previous ones) and combines them following a deterministic strategy bagging, that often considers homogeneous weak learners, learns them independently from each other in parallel and combines them following some kind of deterministic averaging process Ensemble Learning
- 13. • Artificial neural network (ANN) is a system of information processing which is inspired by the human brain’s neural network. Neural Network Learning A biological neuron An artificial neuron
- 14. • Supervised Neural Network • Unsupervised Neural Network • Reinforced Neural Network Types of Neural Network Learning
- 15. This is also called memory-based learning which compares new problem instances with instances seen in training, which have been stored in memory. • K-Nearest Neighbor (KNN). Instance Based Learning
- 16. • Web search • Computational biology • Finance • E-commerce • Space exploration • Robotics • Information extraction • Social networks • Debugging • [Your favorite area] Applications
- 17. Conclusion and Future Scope We have a simple overview of some techniques and algorithms in machine learning. Each technique can be used in different application areas and based on the advantages of each algorithm; it is useful in different domains. Furthermore, there are more and more techniques apply machine learning as a solution. In the future, machine learning will play an important role in our daily life.
- 18. • Welling, Max. "A first encounter with Machine Learning." Irvine, CA: University of California 12 (2011). • Bowles, Michael. Machine learning in Python: essential techniques for predictive analysis. John Wiley & Sons, (2015). • Kotsiantis, Sotiris B., I. Zaharakis, and P. Pintelas. "Supervised machine learning: A review of classification techniques." Emerging artificial intelligence applications in computer engineering 160 (2007): 3-24. • Hu, Yuh-Jyh, et al. "Decision tree-based learning to predict patient controlled analgesia consumption and readjustment." BMC medical informatics and decision making 12.1 (2012): 131. • Lowd, Daniel, and Pedro Domingos. "Naive Bayes models for probability estimation." Proceedings of the 22nd international conference on Machine learning. ACM, 2005. • Uddin, Muhammad Fahim, Soumita Banerjee, and Jeongkyu Lee. "Recommender system framework for academic choices: Personality based recommendation engine (PBRE)." 2016 IEEE 17th International Conference on Information Reuse and Integration (IRI). IEEE, 2016. • Saputra, Muhammad Firman Aji, Triyanna Widiyaningtyas, and Aji Prasetya Wibawa. "Illiteracy Classification Using K Means-Naïve Bayes Algorithm." JOIV: International Journal on Informatics Visualization 2.3 (2018): 153-158. • Shalev-Shwartz, Shai, et al. "Pegasos: Primal estimated sub-gradient solver for svm." Mathematical programming 127.1 (2011): 3-30. • Lim, Chungsoo, Seong-Ro Lee, and Joon-Hyuk Chang. "Efficient implementation of an SVM-based speech/music classifier by enhancing temporal locality in support vector references." IEEE Transactions on Consumer Electronics 58.3 (2012): 898-904. • Dey, Ayon. "Machine learning algorithms: a review." International Journal of Computer Science and Information Technologies 7.3 (2016): 1174-1179. • Zhou, Pei-Yuan, and Keith CC Chan. "A model-based multivariate time series clustering algorithm." Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2014. • Zhu, Xiaojin, and Andrew B. Goldberg. "Introduction to semi-supervised learning." Synthesis lectures on artificial intelligence and machine learning 3.1 (2009): 1-130. • Zhu, Xiaojin Jerry. Semi-supervised learning literature survey. University of Wisconsin-Madison Department of Computer Sciences, 2005. • Dey, Ayon. "Machine learning algorithms: a review." International Journal of Computer Science and Information Technologies 7.3 (2016): 1174-1179. • Harrington, Peter. Machine learning in action. Manning Publications Co., (2012). • Andrecut, Mircea. "Parallel GPU implementation of iterative PCA algorithms." Journal of Computational Biology 16.11 (2009): 1593-1599. • Dey, Ayon. "Machine learning algorithms: a review." International Journal of Computer Science and Information Technologies 7.3 (2016): 1174-1179. • Caruana, Rich. "Multitask learning." Machine learning 28.1 (1997): 41-75.D. • Opitz, David, and Richard Maclin. "Popular ensemble methods: An empirical study." Journal of artificial intelligence research 11 (1999): 169-198. • Zhang, Min-Ling, and Zhi-Hua Zhou. "Exploiting unlabeled data to enhance ensemble diversity." Data mining and knowledge discovery 26.1 (2013): 98-129. • Kim, Dong Gil, et al. "Developing of New a Tensorflow Tutorial Model on Machine Learning: Focusing on the Kaggle Titanic Dataset." IEMEK Journal of Embedded Systems and Applications 14.4 (2019): 207-218. • V. Sharma, S. Rai, A. Dev, “A Comprehensive Study of Artificial Neural Networks”, International Journal of Advanced Research in Computer Science and Software Engineering, ISSN 2277128X, Volume 2, Issue 10, (2012) • Hiregoudar, S. B., K. Manjunath, and K. S. Patil. "A survey: research summary on neural networks." International Journal of Research in Engineering and Technology 3.15 (2014): 385-389. • Instance-based learning, https://en.wikipedia.org/wiki/Instance-based_learning,14.10.2019 References
- 19. Thank You