| Topic | Slides | |
| Introduction | intro.pptx | |
| Linux scheduling | scheduling1.pdf, scheduling2.pdf | |
| Real Time Systems | realtime1.pdf, realtime2.pdf, realtime3.pdf | |
| FreeRTOS | FreeRTOS Book | Chapters 3,4,5,7,8 |
| Linux device drivers, hal/ll | Embedded Linux, Device Tree, | Linux Device Driver, STM32 HAL LL libraries |
| Minor Exam Syllabus till this | ||
| Embedded Machine Learning inferences |
Embedded ML overview embeddedML_overview.pdf ML Model Architecture changes to reduce computations and storage: (i) Original computations and storage needed in basic CNN forward pass cnn-basics.pdf, (ii) 1x1 bottleneck layer inception-1x1-bottlenecklayer.pdf, Andrew NG video, (iii) depthwise separable convolutions mobilenet-depthwise-separable-convolution.pdf ML model compression technqiues: (i) Quantization quantization.pdf, (ii) Pruning pruning.pdf |
Additional online resources on ML model compression: tensorflow, tensorflowlite, ristretto, pytorch, STM32, nvidia tensorrt, tensorrt sample script |
| Security of embedded platforms and privacy of data collected with embedded platforms | 1. System security (virus example for reverse_tcp connection on Windows) and network security (nMap for port scanning, ssh and tomcat brute force attacks on Metasploitable), defence mechanism using write detection and write protection security.pdf 2. Why privacy is not just a technical problem dataprivacy.pdf, one technical method for data privacy, namely secure multi-party computation with garbled circuit garbledcircuit_slides.pdf, garbledcircuit_video.mp4. Handout from John Hopkins garbledcircuit_handout.pdf |
1. Example of applying secure MPC for an embedded/mobile application secureMPC_example.pdf 2. Wikipedia article on Yao's garbled circuit Yao's GC |
| Revisiting embedded Machine Learning inferences |
1. The difference between Gen1 and Gen2 NN compilers NNcompilers.pdf 2. Gen2 NN compiler ANSOR_paper.pdf, ANSOR_slides.pdf 3. Runtime management in an inference serving system NNruntime.pdf, nexus.pdf |
list of 10 papers that students presented, on compilers and runtime for inferences at paperlist |
| Major Exam Syllabus till this |