Lecture 24 - Course Summary | MIT 6.S965
Lecture 24 summarizes the course.
Slides: https://efficientml.ai/schedule/
------------------------------------------------------------------------------------
TinyML and Efficient Deep Learning Computing
Instructors:
Song Han: https://songhan.mit.edu
Have you found it difficult to deploy neural networks on mobile devices and IoT devices? Have you ever found it too slow to train neural networks? This course is a deep dive into efficient machine learning techniques that enable powerful deep learning applications on resource-constrained devices. Topics cover efficient inference techniques, including model compression, pruning, quantization, neural architecture search, and distillation; and efficient training techniques, including gradient compression and on-device transfer learning; followed by application-specific model optimization techniques for videos, point cloud, and NLP; and efficient quantum machine learning. Students will get hands-on experience implementing deep learning applications on microcontrollers, mobile phones, and quantum machines with an open-ended design project related to mobile AI.
Website:
http://efficientml.ai/
Видео Lecture 24 - Course Summary | MIT 6.S965 канала MIT HAN Lab
Slides: https://efficientml.ai/schedule/
------------------------------------------------------------------------------------
TinyML and Efficient Deep Learning Computing
Instructors:
Song Han: https://songhan.mit.edu
Have you found it difficult to deploy neural networks on mobile devices and IoT devices? Have you ever found it too slow to train neural networks? This course is a deep dive into efficient machine learning techniques that enable powerful deep learning applications on resource-constrained devices. Topics cover efficient inference techniques, including model compression, pruning, quantization, neural architecture search, and distillation; and efficient training techniques, including gradient compression and on-device transfer learning; followed by application-specific model optimization techniques for videos, point cloud, and NLP; and efficient quantum machine learning. Students will get hands-on experience implementing deep learning applications on microcontrollers, mobile phones, and quantum machines with an open-ended design project related to mobile AI.
Website:
http://efficientml.ai/
Видео Lecture 24 - Course Summary | MIT 6.S965 канала MIT HAN Lab
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Tutorial - Training Deep Nets with PyTorch | MIT 6.S965TSM: Temporal Shift Module for Efficient Video Understanding, online demo with NVIDIA NanoEfficientML.ai Lecture 9 - Knowledge Distillation (MIT 6.5940, Fall 2023)Lecture 08 - Neural Architecture Search (Part II) | MIT 6.S965Lecture 04 - Pruning and Sparsity (Part II) | MIT 6.S965TorchQuantum Tutorial Opening: Intersection of Quantum and Machine LearningEfficientML.ai Lecture 6 - Quantization (Part II) (MIT 6.5940, Fall 2023, Zoom recording)Lecture 04 - Pruning and Sparsity (Part II) | MIT 6.S965EfficientML.ai Lecture 16 - Diffusion Model (MIT 6.5940, Fall 2023, Zoom)MCUNet for Visual Wake Words with 10KB MemoryMCUNetV2 DemoStreamingLLM LectureLecture 25 - AI Model EfficiencyToolkit (AIMET) | MIT 6.S965Lecture 22 - Quantum Machine Learning | MIT 6.S965EfficientML.ai Lecture 6 - Quantization (Part II) (MIT 6.5940, Fall 2023)Online-TSM on Ultra96V2 and FPGAEfficientML.ai Lecture 18: Distributed Training (Part II) (MIT 6.5940, Fall 2023)Lecture 17 - TinyEngine - Efficient Training and Inference on Microcontrollers | MIT 6.S965Micro'21 PointAcc: Efficient Point Cloud AcceleratorMCUNet TinyML Use Cases