# Machine Learning Lecture 10: Neural Networks and Deep Learning Feng Li fli@sdu.edu.cn https://funglee.github.io School of Computer Science and Technology Shandong University Fall 2018 ## Deep Feedforward $ is usually a highly non-linear function • Feedforward networks are of extreme importance to machine learning practitioners - The conventional neural networks (CNN) used for object recognition from

## Machine Learning Pytorch Tutorial TA：曾元(Yuan Tseng) 2022.02.18 ## Outline Background: Prerequisites & What is Pytorch? • Training & Testing Neural Networks in Pytorch • Dataset & Dataloader [Image](/uploads/documents/7/6/e/1/76e1a67e96719ae74c41b110fe07bfe6/p3_2.jpg) ## What is PyTorch? - An machine learning framework in Python. • Two main features: ○ N-dimensional Tensor computation (like NumPy) & speech) ESPnet (speech recognition, translation, synthesis, ...) ☐ Most implementations of recent deep learning papers ○ ... ## References • Machine Learning 2021 Spring Pytorch Tutorial • Official

## Debugging the BPF Virtual Machine eBPF Summit ## Why? ● Debugging is useful to understand how things work ● Sometimes, eBPF programs can’t even load - I couldn’t find good resources on this, so so, here I am ● I break lots of eBPF programs - The BPF Virtual machine is not easy to understand ## The approach ## The BPF subsystem lives in the kernel ![Image](/uploads/documents/7/1/6/1/7161fc3

Back to Basics: The Abstract Machine Bob Steagall CppCon 2020 ## KEWB COMPUTING ## Overview/Goals • Describe abstract machines in general • Describe the C++ abstract machine specifically • Language goals • Important components of the abstract machine, and their relationships • Provide a useful overview of the C++ abstract machine ## What is an Abstract Machine? “Abstract machines are machines because between the high level of a programming language and the low level of a real machine. The instructions of an abstract machine are tailored to the particular operations required to implement operations of

# Lecture Notes on Support Vector Machine Feng Li fli@sdu.edu.cn Shandong University, China ## 1 Hyperplane and Margin In a n-dimensional space, a hyper plane is defined by $$ \omega^{T}x+b=0 $$ 7b9d33d07aa393893fb3862bcd67/p2_1.jpg) Figure 1: Margin and hyperplane. ## 2 Support Vector Machine ### 2.1 Formulation The hyperplane actually serves as a decision boundary to differentiating positive we can construct a infinite number of hyperplanes, but which one is the best? Supported Vector Machine (SVM) answers the above question by maximizing $ \gamma $ (see Eq. (6)) as follows $$ \begin

## Lecture 6: Support Vector Machine Feng Li Shandong University fli@sdu.edu.cn December 28, 2021 ## Outline  1 SVM: moving it parallelly along $ \omega $ (b < 0 means in opposite direction) ## Support Vector Machine • A hyperplane based linear classifier defined by $ \omega $ and b • Prediction rule: $ y = [Image](/uploads/documents/4/1/3/0/41305aec36322a1beae76d1d88486b9a/p14_2.jpg) ## Support Vector Machine (Primal Form) • Maximizing $ 1/\|\omega\| $ is equivalent to minimizing $ \|\omega\|^{2}=\omega^{T}\omega

## Yandex ## Yandex # Machine Learning with ClickHouse ## Experimental dataset ## NYC Taxi and Uber Trips > Where to download: https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page > with categorical features support out of the box for Python, R https://catboost.yandex Edit machine-learning decision-trees gradient-boosting gbm gödt python kaggle gpu-computing tutorial

## Yandex ## Yandex # Machine Learning with ClickHouse ## Experimental dataset ## NYC Taxi and Uber Trips > Where to download: https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page > with categorical features support out of the box for Python, R https://catboost.yandex Edit machine-learning decision-trees gradient-boosting gbm gödt python kaggle gpu-computing tutorial

# Solving Nim by the Use of Machine Learning Exploring How Well Nim Can be Played by a Computer Mikael Nielsen Røykenes  sciences UNIVERSITY OF OSLO Autumn 2019 Powered by TCPDF (www.tcpdf.org) # Solving Nim by the Use of Machine Learning Exploring How Well Nim Can be Played by a Computer Mikael Nielsen Røykenes ![Image] fd42ee4fc534c2ea67eaa32cea/p3_1.jpg) © 2019 Mikael Nielsen Røykenes Solving Nim by the Use of Machine Learning http://www.duo.uio.no/ Printed: Reprosentralen, University of Oslo ## Contents 1 Intro

## I s Your Virtual Machine Really Ready-to-go with Istio? Kailun Qin, Intel Haoyuan Ge ## I stioCon Quick Summary (from Google Cloud Next '19 [1]) ## V M works on Istio! ## Why Add VMs to the 591b1719e6/p13_2.jpg) #### V 1.6-1.8 Better VM Workload Abstraction |Item|Kubernetes|Virtual Machine| |---|---|---| |Basic schedule unit|Pod|WorkloadEntry| |Component|Deployment|WorkloadGroup| |Service ☑ Documents available ☐ Virtual Machine Installation to get started. Virtual Machine Architecture to learn about the high level architecture of Istio’s virtual machine integration. Debugging Virtual