(IBM) Natural Language Processing & AI: From Theory to Practice
About This Course
This course is designed for professionals with foundational knowledge in programming and machine learning who want to develop natural language processing capabilities. Whether you're working in data analytics, technology, or automation, this course will equip you with techniques for text classification, deep learning for NLP, language modelling, and advanced architectures for sequence-to-sequence tasks.
What You'll Learn
LO1: Analyse the application areas of NLP and identify common tasks associated with text data.
LU2: Deep Learning Foundations for NLP
LO2: Apply deep learning concepts and architectures to NLP tasks.
LO3: Implement and optimise neural networks using backpropagation and matrix calculus for NLP applications.
LU3: Word Embeddings and Similarity Measures
LO4: Evaluate and implement various word embedding techniques, comparing count-based and prediction-based methods.
LO5: Apply and analyse similarity measures for word semantics in NLP tasks.
LU4: Text Classification and Language Models
LO6: Develop and evaluate deep learning models for text classification, incorporating regularisation techniques and appropriate loss functions.
LO7: Construct and compare n-gram language models and recurrent neural networks (RNNs) for text modeling.
LU5: Advanced NLP Architectures
LO8: Design and implement encoder-decoder models for sequence-to-sequence NLP tasks.
LO9: Develop memory networks for complex NLP tasks and determine strategies for their augmentation.
LU6: Advanced NLP Techniques
LO10: Apply Bayesian methods to NLP problems and evaluate their effectiveness compared to other approaches.
LO11: Implement and analyse various parsing techniques for natural language understanding.
Entry Requirements
• Possess minimally a 'N' Level and/or listen, speak, read, and write English at a proficiency level equivalent to Employability Skills System Workplace Literacy (WPL) Level 4.
• Use numeracy skills equivalent to the Employability Skills System Workplace Numeracy (WPN) Level 3.
• Learners should have proficiency in Python programming and an understanding of fundamental deep learning principles. Familiarity with neural networks and basic calculus is recommended.
• Learners without the prerequisite may be accepted into the course if they have at least 1 year of relevant work experience.