basic machine learning concepts mathematical notations principles of learning linear regression overfitting regularization Vectors, Matrices and Norms

팩맨dfs bfs

Paging: Introduction

메모리 가상화OS virtualizes its physical memory.OS provides an illusion memory space per each process.It seems to be seen like each process uses the whole m

In this chapter, we study very simple file system (vsfs)Basic on-disk structures, access methods, and various policies of vsfsWe will study...How can

Feedforward neural network (FFNN) as MLP• Information only flows in one direction.• No sense of time or memory for previous data.Recurrent neural netw

Variational Auto-Encoder (VAE)• AE encoder directly produces a latent vector z (single value for each attribute).Then, AE decoder takes these values t

Auto-Encoder (AE)• Auto-Encoder is an unsupervised learning for data reconstruction by encoding-decoding.Specifically, its bottleneck network forces a

Generative Adversarial Network (GAN)• GenerativeLearn a generative model• AdversarialTrained in an adversarial setting: generator G and discriminator

I/O is critical to computer system to interact with other systems.Issue :How should I/O be integrated into systems? What are the general mechanisms? H

$yi=x_i^3+x{i-1}^2+x\_{i-2}$배웠다

CNN-LSTM model for Image Captioning > Image Captioning은 이미지를 언어로 설명하는 작업이다. > CNN as an encoder is used to learn features in images. LSTM as a decode

순환 신경망(Recurrent neural network, RNN)• RNN (LSTM) makes predictions based on current and previous inputs recurrently,while FFNN makes decisions based

• CNN has great success in computer vision applications, especially in image classification,based on its shared weights using Convolution and translat

Goal of Cache Managementto minimize the number of cache misses.the average memory access time(AMAT)Lead to the fewest number of misses overall.Replace

네트워크 계층의 호스트 사이의 통신 서비스 제공네트워크 계층은 트랜스포트 계층이나 애플리케이션 계층과는 달리, 각 호스트와 네트워크의 라우터마다 네트워크 계층의 일부가 존재한다.네트워크 계층은 서로 상호작용하는 데이터 평면Data Plane과 제어 평면Control P