Objective
Wave acoustics; Principles of sound production and sound perception; Production of speech and music signals; Fundamentals of discrete-time signal processing; Time-domain and frequency-domain methods of speech processing; Linear predictive analysis of speech; Properties of music and other audio signals; Periodicity and harmonics; Pitch extraction; Speech and audio coding techniques; Introduction to speech and music synthesis.
Syllabus
Learning Outcome
Wave acoustics; Principles of sound production and sound perception; Production of speech and music signals; Fundamentals of discrete-time signal processing; Time-domain and frequency-domain methods of speech processing; Linear predictive analysis of speech; Properties of music and other audio signals; Periodicity and harmonics; Pitch extraction; Speech and audio coding techniques; Introduction to speech and music synthesis.
Objective
Introduction: television standards, digital image representation, statistical models, basic lossless and lossy coding techniques; advanced coding techniques: wavelet coding, synthetic-natural hybrid coding, post-processing techniques; image coding standards: JPEG, JPEG 2000; video coding standards: H.261, H.263, MPEG1, MPEG2, MPEG4; HDTV standard.
Syllabus
Learning Outcome
By the end of the course, students should be able to
Objective
Syllabus
Learning Outcome
Objective
This course provides an introduction to deep learning. Students taking this course will learn the theories, models, algorithms, implementation and recent progress of deep learning, and obtain empirical experience on training deep neural networks. The course starts with machine learning basics and some classical deep models (including convolutional neural network, deep belief net, and auto-encoder), followed by optimization techniques for training deep neural networks, implementation of large-scale deep learning, multi-task deep learning, transferred deep learning, recurrent neural networks, applications of deep learning to computer vision and speech recognition, and understanding why deep learning works. The students taking are expected to have some basic background knowledge on calculus, linear algebra, probability, statistics and random process as a prerequisite.
Syllabus
This course provides an introduction to deep learning. Students taking this course will learn the theories, models, algorithms, implementation and recent progress of deep learning, and obtain empirical experience on training deep neural networks. The course starts with machine learning basics and some classical deep models (including convolutional neural network, deep belief net, and auto-encoder), followed by optimization techniques for training deep neural networks, implementation of large-scale deep learning, multi-task deep learning, transferred deep learning, recurrent neural networks, applications of deep learning to computer vision and speech recognition, and understanding why deep learning works. The students taking are expected to have some basic background knowledge on calculus, linear algebra, probability, statistics and random process as a prerequisite.
Learning Outcome
Understand the fundamental concepts, theories and algorithms of deep learning. 2. Understand why deep learning outperforms other machine learning methods when the training data is in large scale 3. Understand the principles of designing different deep models for various applications 4. Implement and train deep neural networks with deep learning toolboxes 5. Obtain empirical experience of designing and training deep models in practical applications.
Objective
Review of semiconductor fundamentals: electron and hole, Fermi energy, generation and recombination, p-n junction, hopping, field-effect. Introduction to organic and polymeric semiconductors: morphology, molecular packing, conformation, electronic structures, optical and electrical properties. Application of organic/polymeric thin films: OLEDs, OTFTs, PLEDs, photodetectors and sensors. Fabrication methods for flexible electronics: sputtering, CVD, VPD, inkjet printing, screen printing, roll-to-roll printing, spraying coating, etc. Introduction to OLED/PLED based display technology: passive matrix OLED and active matrix OLED display techniques. Basic principles of photovoltaic devices: absorption, photo-electric conversion, conversion efficiency, loss mechanism, carrier collection, device characterization. Introduction to solar cell technology: monocrystalline solar cells; dye-sensitized solar cells; organic solar cells.
Syllabus
Learning Outcome
By the end of the course, students should be able to