ECE 598 NS: Machine Learning in Silicon

Lecture Notes 2017

2017/08/28 Introduction [PDF]
2017/08/30 The Least Mean-Square (LMS) Algorithm and Architecture [PDF] (revised 2017/09/06)
2017/09/11 Fixed-point LMS [PDF] (revised 2017/09/13)
2017/09/13 Algorithm‐to‐Architecture Mapping Techniques [PDF] (revised 2017/09/20)
2017/09/20 Energy-Delay Tradeoffs [PDF] (revised 2017/09/25)
2017/09/27 Single Stage Classifiers - ADALINE, Perceptron [PDF]
2017/09/27 Single Stage Classifiers - Support Vector Machines [PDF]
2017/10/11 Single Stage Classifiers - Training of Support Vector Machines [PDF]
2017/10/11 Ensemble Methods - AdaBoost and Random Forest [PDF] (revised 2017/10/16)
2017/10/18 Deep Learning [PDF] (revised 2017/10/23)
2017/10/23 Deep Learning Case Study [PDF]

2016/08/25 Machine Learning System‐on‐a‐Chip Design [PDF]
2016/08/30 The Least Mean‐Square (LMS) Algorithm and Architecture [PDF]
2016/09/06 Learning in Fixed-Point [PDF] (revised 2016/09/30)
2016/09/15 Algorithm‐to‐Architecture Mapping Techniques [PDF]
2016/09/20 Energy‐Delay Trade‐offs [PDF]
2016/09/22 Making Decisions [PDF]
2016/09/29 Single Stage Kernels – Logistic Regression, ADALINE, & Perceptron [PDF]
2016/10/11 Single Stage Classifiers – The Support Vector Machine (SVM) [PDF]
2016/10/13 Training via the Stochastic Gradient Descent Algorithm (SGD) [PDF]
2016/10/25 Classifier Ensembles ‐ Boosting [PDF] (revised 2016/11/01)
2016/10/27 Classifier Ensembles – Random Forest [PDF]
2016/11/03 Deep Learning [PDF]
2016/11/10 DNN Case Study – DianNao [PDF]
2016/11/10 CNN Case Study – Eyeriss [Link]
2016/11/15 The Belief Propagation (BP) Algorithm [PDF]
2016/11/29 Shannon‐inspired Statistical Computing [PDF]
2016/12/01 Clustering and Related Algorithms [PDF]