Data Science and Artificial Intelligence: The Application of Deep Learning in Natural Language Processing

Course 7: Data Science and Artificial Intelligence: The Application of Deep Learning in Natural Language Processing

I. Course Description

Machine learning is a technique that allows computer systems to learn through data and improve their performance. Natural language processing is the field of studying how computers understand and generate human natural language. Its goal is to enable computers to understand text and speech like humans, and to have natural language interactions with humans. The development of NLP has benefited from advances in machine learning and deep learning technologies that allow computers to better process and understand natural language. Machine learning and natural language processing are two rapidly developing areas, and the application of machine learning to natural language processing has driven great advances in the field of artificial intelligence, such as machine translation systems such as Google Translate, and voice assistants such as Apples Siri. The continuous evolution of machine learning and natural language processing will continue to shape future technological developments and change the way we interact with computers.

The goal of this course is to provide students with the necessary skills needed to conduct high-quality research and to extract actionable insights from the data and make predictions. This course will provide students with a basic knowledge base for applied machine learning using the Python programming language. Students will learn important data collation, feature selection, model selection and model validation techniques within a statistical and probabilistic framework, focusing on text analysis and natural language processing. The aim is not only to expose students to modeling techniques, but also to have students build true working systems through modules they create in their classes and homework exercises. In addition, students will be exposed to various common tools used by data scientists by extracting insights and making predictions from advertising technology, fintech, and marketing technology data sets.

II. Professor Introduction

Patrick Houlihan – Professor at Columbia University

Professor Patrick Houlihan is a professor of data science at Columbia University, who received his PhD in financial engineering from the Stevens Institute of Technology. He is also the senior vice president of decision-making at Publicis Media Group, the largest advertising and communications group in France and the third largest in the world. In addition, he is the co-founder of CaliberMind data scientist, a B2B customer data platform, and Sentiquant, a financial data analytics company.

Professor Patrick Houlihan has more than 14 years of professional experience in the semiconductor industry, leading consulting engineering amount more than five hundred million dollars, published hundreds of papers in the field of software system design and data analysis, such as the use of social media to predict asset prices continue and reverse, the sentiment analysis and options can predict future earnings?》 class.

III. Syllabus

1. Syntax, variables, operators, regular expression, date and time, semantic character, GitHub
2. Set, dictionary, list, for loop, while loop, do loop, I / O read and write
3. Data collation, data cleaning, dimension reduction, normalization and interpolation
4. Natural language processing: text partitioning, stem extraction, feature matrix, and brief introduction
5. Feature selection: TF-IDF, feature vector, and N-gram method
6. Text summary: Text summary and extraction, theme modeling, and keyword extraction
7. Affective analysis: dictionary and machine learning, and model selection
8. Grid search, validation and evaluation, and performance indicators
9. Topic Modeling in Natural Language Processing: Potential Dirichlet Allocation (LDA)
10. Advanced machine learning models for sentiment analysis