Arthur 金 znxkznxk1030

면접질문 리스트
- ML/DL
Receiver Operating Characteristic Curve란 무엇인가?

Statistic & Probability

Statistic & Probability Terminology

단어	원어	설명	표기
확률 변수	Random Variable, Stochastic Variable	측정 값이 변할 수 있는 확률이 주어진 변수	X
확률 분포	Probability Distribution	확률 변수가 특정한 값을 가질 학률을 나다내는 함수
기대값	Expected Value	어떤 확률을 가진 사건을 무한히 반복했을 경우 얻을 수 있는 값의 평균으로서 기대할 수 있는 값. 이산 확률 분포에서는 확률 질량 함수(PMF, Probability Mass Function), 연속 확률 분포에서는 확률 밀도 함수(PDF, Probability Density Function) 이다.	$E = \sum_x x f(x) \ E = \int_{-\infty}^{\infty} x f(x)$
평균값	Mean	확률/통계에서 기댓값을 (모)평균 (Population Mean)이라고도 부른다. 기대값 $\simeq$ 평균값	$E(X)$ 또는 $\mu$

Linear Algebra

Linear Function

Additivity

$$ L(n + v) = L(n) + L(v) $$

Homogeneity $$ L(cv) = cL(v)$$

Machine Learning

Regression vs Classification

	Regression	Classification
목표	연속적인 수치 예측	이산적인 클래스 예측
평가지표	MSE, MAE 등	정확도, 정밀도, 재현율, F1-Measure 등
예시	주택 가격 예측, 기온 변화 예측	이메일이 스팸인지, 이미지가 고양이인지 개인지 분류

Large Language Models: A Survey

Abstract

Abstract—Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks, since the release of ChatGPT in November 2022. LLMs’ ability of general-purpose language understanding and generation is acquired by training billions of model’s parameters on massive amounts of text data, as predicted by scaling laws [1], [2]. The research area of LLMs, while very recent, is evolving rapidly in many different ways. In this paper, we review some of the most prominent LLMs, including three popular LLM families (GPT, LLaMA, PaLM), and discuss their characteristics, contributions and limitations. We also give an overview of techniques developed to build, and augment LLMs. We then survey popular datasets prepared for LLM training, fine-tuning, and evaluation, review widely used LLM evaluation metrics, and compare the performance of several popular LLMs on a set of representative benchmarks. Finally, we co

	let fs = require('fs');

	try {
	let code = fs.readFileSync('in.txt', 'utf8');
	// console.log(code);

	let codelines = code.split("\n").map(codeline => {
	return "\"" + codeline.replace("\r","") + "\""
	}).join(",\n");

	{
	// Place your snippets for javascript here. Each snippet is defined under a snippet name and has a prefix, body and
	// description. The prefix is what is used to trigger the snippet and the body will be expanded and inserted. Possible variables are:
	// $1, $2 for tab stops, $0 for the final cursor position, and ${1:label}, ${2:another} for placeholders. Placeholders with the
	// same ids are connected.
	// Example:
	"Print to console": {
	"prefix": "log",
	"body": [
	"console.log('$1');",

	let input = [[3,1,1],[2,5,1],[1,5,5],[2,1,1]]
	let y = 4;
	let x = 3;

	function init3d(x, y) {
	let dp = new Array(y);
	for (let i = 0; i < y; i++ ) {
	dp[i] = new Array(x + 2);
	for (let j = 0; j < x + 2; j++ ) {
	dp[i][j] = new Array(x + 2);


	import Board

	main = do
	let board = initboard
	putStr $ showBoard board

	module Board (
	Cell(..),
	Row,
	Board,
	initboard,
	showBoard
	) where

	import Data.List