Introduction to-machine-learning
Download as PPTX, PDF4 likes2,818 views
The document provides an introduction to machine learning, covering its definition, types such as supervised, unsupervised, and reinforcement learning, as well as key concepts like decision trees, random forests, and neural networks. It discusses the applications of deep learning, forecasting, and the performance measurement of machine learning algorithms while highlighting common pitfalls such as overfitting and machine bias. Additionally, it includes examples and references for further exploration of machine learning topics.
Introduction to-machine-learning
- 1. Introduction to Machine Learning Babu Priyavrat
- 2. Contents • What is Machine Learning? • Types of Machine Learning • Decision Tree and Random Forests • Neural Network • Deep Learning • Forecasting • Measuring Performance of ML algorithms • Pitfalls of Machine Learning
- 3. What is Machine Learning? • Definition by Arthur Samuel - Machine Learning is a technique which gives "computers the ability to learn without being explicitly programmed.“ • To mimic human intelligence or human learning process
- 4. Evolution of Machine Learning
- 5. How Humans learn? • Knowledge Transfer –attending lecture • Hit and Trial – learning cycling during your childhood What is actually happening? • Categorization • Prediction
- 6. We asked Machines to do same • Categorization • Prediction
- 7. Supervised Machine learning • Formal boring definition - Supervised learning task of inferring a function from labeled training data. The training data consist of a set of training examples. In supervised learning, each example is a pair consisting of an input object (typically a vector) and a desired output value (also called the supervisory signal). • Layman term – Make computers learn from experience • Task Driven
- 9. Example of supervised Machine Learning Categorization Categorizing whether tumor is malignant or benign Prediction (Regression) Predicting the house of price in given area
- 10. How is Supervised Learning Achieved? • The existing data is usually divided into training or testing set. For e.g., Training is usually 70% of data where as Testing is 30% of data. • Algorithm develops it model based on training data • Features important for model is usually selected by humans • Algorithm predicts the results for testing data and later the predicted value is compared with real value to give us accuracy. • Several algorithms are tried until required accuracy is achieved
- 11. UnSupervised Learning Unsupervised learning is a type of machine learning algorithm used to draw inferences from datasets consisting of input data without labeled responses. It is data driven. Clustering a tumor of same kind but doesn’t know it’s nature.
- 12. UnSupervised Learning Examples Network Intrusion detection Clustering your customer base
- 13. Reinforcement Learning • Reinforcement learning is a setting where we have a sequential decision problem. Making a decision now influences what decisions we can make in the future. A reward function is provided that tells us how “good” certain states are. • For e.g., Making robot learn against worthy opponent to play table tennis
- 14. Reinforcement Learning Characteristics • No direct training examples – (delayed) rewards later • Need for exploration of environment or exploitation of environment • The environment might be stochastic and/or unknown • The actions of the learner affects future rewards
- 15. Machine Learning Process in Business
- 16. Decision Tree Decision is a simple representation for Classifying examples. Decision tree learning is one of the most successful techniques for supervised classification learning. For e.g., Surviving Titanic is famous first Machine Learning explanation for Decision Tree
- 17. Random Forest • Random Forest Tree is a Supervised Machine Learning Algorithm Based on Decision Trees. • It is Collective Decisions of Different Decision Trees. • In random forest, there is never a decision tree which have all features of all other decision trees.
- 18. Boosting • Form a large set of simple features • Initialize weights for training images • For T rounds • Normalize the weights • For available features from the set, train a classifier using a single feature and evaluate the training error • Choose the classifier with the lowest error • Update the weights of the training images: increase if classified wrongly by this classifier, decrease if correctly • Form the final strong classifier as the linear combination of the T classifiers (coefficient larger if training error is small)
- 19. Neural Network • a computer system modelled on the human brain and nervous system
- 20. Neural Network Example Predicting whether the person goes to Hospital In next 30 days based on historical Data ( Classification)
- 22. Mar I/O –Neural Network playing Mario ( Reinforcement Learning) https://youtu.be/qv6UVOQ0F44
- 23. Deep Learning
- 24. Applications of Deep Learning Facial Recognition
- 25. Applications of Deep Learning Auto-coloring can be achieved by Algorithmia API
- 26. Applications of Deep Learning https://youtu.be/FroRjEejA30 Semantic segmentation of street for Driverless Car
- 27. How Convolved kernel behaves!
- 28. A Cat!
- 29. Two layers of convolution, activation and pooling with 3 filter layer
- 31. Forecasting • It is usually done on time-series data to predict the future trend • For e.g., forecasting Stock value based on historical data • Usually achieved by ARIMA (Auto- regressive integrated Moving Average) model Amazon stock forecast Amazon actual stock performance
- 32. Measuring performance of ML algorithms
- 33. Pitfalls of Machine Learning • Over fitting • Trying to make algorithm to work only for small set of data • Ignoring Human intuition • Forecasting usually fails because the algorithm is not able to gauge what humans consider valuable. • Machine Bias • For example, a 2015 study found that women were less likely to be shown high-income job ads by Google's AdSense and another study found that Amazon’s same-day delivery service was systematically not available in black neighborhoods, both for reasons that the companies could not explain, but were just the result of the black box methods they used • https://youtu.be/tleeC-KlsKA
- 34. Participate in Machine Learning Competitions http://www.kaggle.com/
- 36. References • https://blogs.nvidia.com/blog/2016/07/29/what s-difference-artificial-intelligence-machine- learning-deep-learning-ai/ • https://blogs.nvidia.com/blog/2014/09/07/imag enet/ • https://www.linkedin.com/learning/machine- learning-essential-training-value-estimations • https://www.slideshare.net/drcfetr/an- overview-of-machine-learning • https://sflscientific.com/blog/2016/12/16/portfol io-prediction • https://ei.is.tuebingen.mpg.de/research_proje cts/robot-skill-learning • https://www.innoarchitech.com/machine- learning-an-in-depth-non-technical-guide-part- 2/ • http://erinshellman.github.io/data-mining- starter-kit/ • http://slideplayer.com/slide/7341084/ • http://machinelearningmastery.com/common- pitfalls-machine-learning-projects/ • https://www.togaware.com/datamining/surviv or/Neural_Network.html • https://read01.com/JNzJkL.html • http://www.papis.io/blog/introduction-to- multi-gpu-deep-learning-with-digits-mike-wang • https://hackernoon.com/visualizing-parts-of- convolutional-neural-networks-using-keras- and-cats-5cc01b214e59