introduction to machine learning and nlp
Download as PPTX, PDF2 likes284 views
The document discusses natural language processing (NLP) and machine learning. It defines NLP as a branch of artificial intelligence that develops systems allowing computers to understand and generate human language. NLP encompasses tasks like machine translation, speech recognition, named entity recognition, text classification, summarization and question answering. The document also discusses the complexities of human language and different levels of linguistic analysis used in NLP, including syntactic, semantic, discourse, pragmatic and morphological analysis.
introduction to machine learning and nlp
- 2. The world is filled with data. Lots and lots of data. Everything from pictures, music, words, spreadsheets, videos and more. It doesn’t look like it’s going to to slow down anytime soon. Machine learning brings the promise of deriving meaning from all of that data. – Yufeng G
- 6. Machine learning Is a field of computer science that gives computers the ability to learn without being explicitly programmed.
- 7. Machine learning “ Using data to answer questions ”
- 8. Types Of Learning Algorithms the type of data they input and output and the type of task or problem that they are intended to solve. Supervised machine learning. unsupervised machine learning Semi-supervised machine learning Reinforcement machine learning
- 9. Supervised Machine Learning build a mathematical model of a set of data that contains both the inputs and the desired outputs The data is known as training data, and consists of a set of training examples
- 10. unsupervised machine learning take a set of data that contains only inputs, and find structure in the data, like grouping or clustering of data points
- 11. Semi-supervised machine learning fall somewhere in between supervised and unsupervised learning, since they use both labeled and unlabeled data for training – typically a small amount of labeled data and a large amount of unlabeled data.
- 12. Reinforcement machine learning learning method that 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 reinforcement learning.
- 13. Classification predict class from observations Regression predict value from observations Clustering group observations into “meaningful” groups Machine Learning Techniques 4 Machine Learning Techniques
- 14. Classification Classification algorithms Classification algorithms are used when the outputs are restricted to a limited set of values, Classification is the process of predicting the class of given data points. Classes are sometimes called as targets/ labels or categories. Classification predictive modeling is the task of approximating a mapping function (f) from input variables (X) to discrete output variables (y).
- 15. Decision Tree Classification algorithm Decision tree builds classification or regression models in the form of a tree structure. It utilizes an if-then rule set which is mutually exclusive and exhaustive for classification. The rules are learned sequentially using the training data one at a time. Each time a rule is learned, the tuples covered by the rules are removed. This process is continued on the training set until meeting a termination condition.
- 16. Naive Bayes Classification algorithm Naive Bayes classifiers are a collection of classification algorithms based on Bayes’ Theorem. It is not a single algorithm but a family of algorithms where all of them share a common principle, i.e. every pair of features being classified is independent of each other. http://blog.aylien.com/naive-bayes-for-dummies-a-simple-explanation/
- 17. Regression Regression algorithms regression algorithms are used when the outputs may have any numerical value within a range. is a measure of the relation between the mean value of one variable (e.g. output) and corresponding values of other variables (e.g. time and cost).
- 18. Linear and Polynomial Regression Regression algorithm https://towardsdatascience.com/selecting-the- best-machine-learning-algorithm-for-your- regression-problem-20c330bad4ef Linear regression is simple to understand which can be very valuable for business decisions. non-linear data, polynomial regression can be quite challenging to design, as one must have some information about the structure of the data and relationship between feature variables.
- 19. Neural Networks Regression algorithm A Neural Network consists of an interconnected group of nodes called neurons. The input feature variables from the data are passed to these neurons as a multi-variable linear combination, where the values multiplied by each feature variable are known as weights.
- 20. Clustering Clustering algorithms is the task of grouping a set of objects in such a way that objects in the same group (called a cluster) are more similar to each other we can use clustering analysis to gain some valuable insights from our data by seeing what groups the data points fall into when we apply a clustering algorithm.
- 21. K-Means Clustering Clustering algorithm type of unsupervised learning, which is used when you have unlabeled data (data without defined categories or groups). The goal of this algorithm is to find groups in the data, with the number of groups represented by the variable K. The algorithm works iteratively to assign each data point to one of K groups based on the features that are provided. Data points are clustered based on feature similarity. The results of the K-means clustering
- 22. Student Performance Prediction System Department of Computer Science / Graduation Project The purpose of this project is to develop a predictive recommender system to help educational institution detect early students at risk and who are not making satisfactory progress and allow institutions to take more proactively holistic approach toward student success. Abstract: Sklearn Library Web Platform Django Framework Backend Framework PostgreSQL Database Use-Cases
- 23. Student Performance Prediction System Department of Computer Science / Graduation Project Use-Cases Project objectives: • Create a web application that will aid in the process of decision making for educators • Educators can give advices to students • Track students • Build a system that predicts students future performance • System will alert in case of predicting failing or low performance • Identify weakness of students • Make recommendations • Students have the availability to give their opinions to educators • Students have the availability to see their performance and weakness
- 24. Student Performance Prediction System Department of Computer Science / Graduation Project Use-Cases https://std-performance.herokuapp.com https://github.com/EslamTK/Students-Performance-System
- 25. Machine Learning Applications Applications for machine learning include Machine Learning Applications Natural language processing Speech recognition General game playing Machine translation opinion mining Classifying DNA sequences Internet fraud detection Structural health monitoring Computer vision Bioinformatics Robot locomotion Recommender systems Search engines Brain–machine interfaces object recognition handwriting recognition PART 2
- 26. (NLP) is a branch of artificial intelligence Why NLP Linguistic analysis Introduction z app
- 27. Natural Language Processing (NLP) is a branch of artificial intelligence Introduction NLP is the branch of computer science focused on developing systems that allow computers to communicate with people using everyday language NLP encompasses anything a computer needs to understand natural language and also generate natural language. NLP is related to human -computer interaction.
- 28. The process of reading and understanding language is far more complex than it seems at first glance. There are many things that go in to truly Natural language processing helps computers communicate with humans in their own language and scales other language-related tasks. For example, NLP makes it possible for computers to read text, hear speech, interpret it, measure sentiment and determine which parts are important. Human language is astoundingly complex and diverse. We express ourselves in infinite ways, both verbally and in writing. Not only are there hundreds of languages and dialects, but within each language is a unique set of grammar and syntax rules, terms and slang. When we write, we often misspell or abbreviate words, or omit punctuation. When we speak, we have regional accents, and we mumble, stutter and borrow terms from other languages. Natural Language Processing (NLP) is a branch of artificial intelligence Why NLP understanding what a piece of text means in the real-world. For example, what do you think the following piece of text means? “Steph Curry was on fire last nice. He totally destroyed the other team”
- 29. Natural Language Processing (NLP) is a branch of artificial intelligence Syntactic . some word sequence may be rejected if they violate the rules of language syntactic analyzer reject the sentence “Boy the go the to store” Semantic Sentence which has no meaning is rejected. For “ colorless green ideas ” has no meaning. Discourse The meaning of an individual sentence may depends on the sentence that precede it and may influence the meaning of sentences that follow it. “john wanted it” the word ‘it’ depends upon john. Pragmatic It means understanding purposeful use of language in situation. “ DO you know what time it is?” should be interpreted as a request. Morphological Individual words are analyzed into their component and nonword tokens. punctuation are separated from word carried= carry + ed Linguistic analysis
- 30. Machine Translation Speech Recognition Named Entity Recognition Text classification Automatic summarization Language Generation Question Answering Natural Language Processing (NLP) is a branch of artificial intelligence app
- 31. Special thanks should be given to : Eng. MIRAN SHAHEEN Many thanks to : ENG. MAI MAGDY • https://en.wikipedia.org/wiki/Machine_learning • https://towardsdatascience.com • https://www.sas.com/en_us • https://www.geeksforgeeks.org/machine-learning/ • https://www.mathworks.com/ • https://www.youtube.com • https://github.com/EslamTK/Students- Performance-System References presented by : M1 , M2 ; Where M1 = Mahmoud Farag And M2 = Mostafa Magdy