In the realm of robotics, Natural Language Processing (NLP) and deep learning are becoming increasingly vital for enabling effective human-robot interaction. Through the application of recurrent neural networks, transformers, and other advanced deep learning techniques, robots can understand, interpret, and generate human language, facilitating more intuitive communication with users. Consequently, students studying robotics must grasp the principles of NLP and deep learning to create advanced systems that can engage with humans naturally and efficiently. This module aims to equip students with the knowledge and skills necessary to train NLP models, optimize their performance, and implement them in real-world robotic applications. As the integration of robots in various sectors grows, so does the need for professionals skilled in both deep learning and NLP techniques. This module aims to enable students to: • Understand the principles and techniques of NLP in the context of robotics. • Explore deep learning algorithms for processing and generating natural language. • Apply NLP and deep learning to enhance human-robot interaction.
Students completing the module successfully should be able to: A. Demonstrate a nuanced understanding of both the theoretical and practical aspects of Natural Language Processing (NLP), distinguishing between various methodologies and their applications in robotic systems. B. Demonstrate knowledge of linguistic principles and the implementation of NLP techniques for tasks such as text classification, sentiment analysis, and language generation using deep learning frameworks. C. Apply theoretical knowledge of deep learning algorithms to develop NLP solutions that address real-world challenges, particularly in enhancing human-robot interactions. D. Develop capabilities to analyze and evaluate the performance of NLP models and algorithms, recognizing their strengths and limitations while proposing modifications and improvements based on an understanding of underlying principles. E. Gain hands-on experience in designing and implementing deep learning pipelines for NLP tasks, including data preprocessing, model selection, training, validation, and evaluation of trained models. F. Train students’ skills and experience in remote operation of Linux GPU servers via terminals to facilitate the development and deployment of NLP
The teaching philosophy of the module follows very much the philosophy of Syntegrative Education. This has meant that the teaching delivery pattern, which follows more intensive block teaching, allows more meaningful contribution from industry partners. This philosophy is carried through also in terms of assessment, with reduction on the use of exams and increase in coursework, especially problem-based assessments that are project focused. The delivery pattern provides space in the semester for students to concentrate on completing the assessments. This module is delivered with a combination of delivery in lectures, laboratory exercise, tutorials and a seminar at the end of the delivery. The concepts introduced during the lecture are illustrated using step-by-step analysis of practical training, complete case studies and live programming tutorials. In the laboratory practice, students will have opportunities to solve a set of exercises during the laboratories under the supervision of the lecturer and the teaching assistant. At the end of each week, there will be a tutorial to emphasize keynotes that have been discussed in lectures and laboratory practice during that week. At the end of the delivery, there will be a seminar to review the whole module delivery.