COURSE OBJECTIVES:
Natural Language Processing (NLP) is the fastest-growing field of deep learning with interest and funding from top AI companies to solve problems of language, text, and unstructured information. This has resulted in a tremendous focus on model building that combines language, mathematics, and computer science.
This 4-weeks course will focus on problems of text summarization, question answering, and sentiment classification using modern approaches to model-building (GNMT, BERT, and GPT2). We will apply this to real-world problems to create an NLP pipeline on top of the PyTorch framework and spaCy.
The course offers both theoretical and practical, lab-heavy modules. By completing you would be able to:
Have working knowledge of PyTorch to train your own deep learning models.
Use OpenVINO to run model optimizer
Use less compute and memory for deploying model inference in production.
Build end to end NLP pipeline with everything you learn
This course is packed with practical exercises and code labs.
* We meet twice a week at online classroom (powered by zoom)
* Practical walkthroughs that present solutions to actual, real-world problems and challenges
* A no-nonsense teaching style that cuts through all the cruft and help you master NLP and Pytorch
COURSE SCHEDULE:
- Session 1: Mar 3, 11am-1pm PST (US Pacific Timezone, GMT-8)
- Session 2: Mar 5, 11am-1pm PST
- Session 3: Mar 10, 11am-1pm PST
- Session 4: Mar 12, 11am-1pm PST
- Session 5: Mar 17, 11am-1pm PDT (US Pacific Timezone, Daylight Saving Time, GMT-7)
- Session 6: Mar 19, 11am-1pm PDT
- Session 7: Mar 24, 11am-1pm PDT
- Session 8: Mar 26, 11am-1pm PDT
COURSE INCLUDE:
- 4 weeks / 8 sessions / 16 hours
- 8 lectures / 4 hands-on code labs/Capstone project
- Live session (with zoom) and real time interaction
- Slack support during/after class
COURSE CONTENT:
Check the Syllabus tab for full course content.
WHO SHOULD LEARN:
Developers, engineers, data scientists
PREREQUISITE:
Python coding skills, intro to PyTorch framework is helpful, ML basics, Use Jupyter notebook on a chrome browser
Difficulty Level
Beginner~Intermediate
Est. time spend per week: 4 hours live class (required) + 2 hours homework/capstone project (optional)
REFUND POLICY
Full refund upon request before the first session ends (Mar 3rd, 2021 1pm PST). 5% transaction fee is not refundable.
SESSION REPLAY
If missed live sessions, you can watch recordings any time, along with interactive learning tools, slides, course notes
Students have one year access to course materials
BENEFITS
Earn Certificate of Completion
Scholarship is available for application, contact for details
PREVIOUS COHORTS:
Cohort 1: Dec. 12, 2020
Module 1: NLP Fundamentals
Learning Objectives: This session will overview NLP tenqiues, transfer learning, and introduce the fundamentals and application of Language Modeling Tools. Your will also learn use NLP pipeline to process documents, Word Vectors
- Fundamentals and application of Language Modeling
- Classical vs Deep Learning NLP
- NLP Pipeline
- Use NLP pipeline to process documents
- POS, Word embedding
- Lab 1 & 2
Module 2: NLP Libraries and Pytorch
Learning Objectives: This session will introduction to key packages and libraries of NLP, and get staryed with SpaCy and Pytorch
- Key packages & libraries in NLP
- Dive into SpaCy
- Intro Pytorch
- Lab 3 & 4
Module 3: Deep Learning for NLP
Learning Objectives: This session will discuss a few important and commonly used NLP techniques and algorithms with deep learning.
- RNN, LSTM with PyTorch
- Using Seq2Seq model for machine translation
- Lab 5
Module 4: Deep Learning for NLP (continued)
Learning Objectives: This session will discuss a few important and commonly used NLP techniques and algorithms with deep learning.
- Text Classification
- Text Summarization
- Lab 6: LSTM based text classifier
- Lab 7: TFIDF and Logistic Regression based classifier
- Lab 8: Multi-label classifier
- Lab 9: Text Summarization
- Capsone project assigment and discussion
Module 5: Transfer Learning and Transformers
Learning Objectives: This session will deep dive into transformer architecture.
- Introduction to Transformers
- Paper review (Attention is All you Need)
- Transfer Learning Fundamentals
- Pre-trained models, such as BERT, XLNet from Huggingface
- Lab 10: Solve NLP problems using PyTorch, pre-trained models
Module 6: Question/Answering with Chatbot
Learning Objectives: This session will discuss Question / Answering through developing a chatbot.
- Overview and theory
- Stanford Question Answering Dataset (SQuAD)
- Lab 11: Develop a chatbot
Module 7: NLP Pipelines
Learning Objective: This session will discuss MLOps using a text classification model
- Scheduler Overview
- Implementation walk-through
- Lab 12
Module 8: NLP in production
Learning Objective: This session will discuss implement NLP in production system
- NLP in production
- capstone project demo
Yashesh Shroff, Ravi Ilango
Ravi IlangoSr. Data Scientist working on a variety of revenue-generating projects for clients involving machine learning and deep learning. He worked as Sr Data Scientist at Apple for 10 years, and a Sr Program Manager at Applied Materials
Yashesh Shroff,PhD
Lead AI of Intel, where he focuses on enabling the AI ecosystem on heterogeneous compute. He has over 15 years of technical and enabling experience, spanning optical modeling, statistical analysis, and capital equipment supply chain at Intel. He has over 20 published papers and 4 patents. He has a Ph.D. in EECS from UC Berkeley