Giter Site home page Giter Site logo

hongik_2020's Introduction

교육 목표

딥러닝을 이해하고 실제 문제에 적용하여 해결할 수 있다.


교육 상세 목표

  • 딥러닝을 이해한다.
  • 딥러닝을 적용할 수 있는 문제를 이해한다.
  • 딥러닝을 실 문제에 적용하는 방법을 이해한다.
  • 딥러닝에 적용하기 위한 데이터 처리방법을 이해한다.
  • 데이터 처리방법을 파악하고 구현할 수 있다.
  • 딥러닝을 적용하여 실제 문제를 해결한다.

대상

선수 교육(python, numpy, pandas)를 아는 개발자.

일자별 계획

1일차

딥러닝 이해


2일차

Keras로 구현한 딥러닝 코드


3일차

분류기로서의 DNN


CNN


4일차

다양한 활용


실제 영상인식


5일차

Functional API

다양한 활용



6일차

다양한 활용


RNN, 강화학습



7일차

GAN


8일차

Object Detection


9일차

다양한 활용


Kaggle 문제 풀이 설명


10일차

딥러닝 교육

  • SW 산업에 대하여
  • SW 개발 이란
  • 딥러닝 개발 계획 리뷰
  • 채용 공고 리뷰

기타

교육환경, numpy, pandas, matplot

  • 교육 환경 : env.md
  • numpy : 데이터 로딩, 보기, 데이터 변환, 형태 변경 : library.md
  • linux 기본 명령어 :
  • pandas, matplot : ibrary.md

기타 자료


딥러닝 활용을 위한 지식 구조

Environment
    jupyter
	colab
	usage
		!, %, run
    GCP virtual machine
linux
	ENV
	command
		cd, pwd, ls
		mkdir, rm, cp
		head, more, tail, cat
	util
		apt
		git, wget
		grep, wc, tree
		tar, unrar, unzip
	gpu
		nvidia-smi

python
	env
		python
			interactive
			execute file
		pip
	syntax
        variable
        data
            tuple
            list
            dict
            set
        loop
        if
        comprehensive list
        function
        class
	module
		import

libray
    numpy
        load
        op
        shape
        slicing
        reshape
        axis + sum, mean
    pandas
        load
        view
        to numpy
    matplot
        draw line graph
        scatter
        show image

Deep Learning
    DNN
        concept
            layer, node, weight, bias, activation
            cost function
            GD, BP
        data
            x, y
            train, validate, test
            shuffle
        learning curve : accuracy, loss
        tunning
            overfitting, underfitting
            regularization, dropout, batch normalization
            data augmentation
        Transfer Learning
    type
        supervised
        unsupervised
        reinforcement
    model
        CNN
            varnilla, VGG16
        RNN
        GAN
    task
        Classification
        Object Detection
        Generation
	Segmentation
	Pose Extraction
	Noise Removing
	Super Resolution
	Question answering
	Auto Captioning
        target : text/image

TensorFlow/Keras
    basic frame
        data preparing
            x, y
            train, valid, test
            normalization
            ImageDataGenerator
        fit
        evaluate
        predict
    model
        activation function
        initializer
    tuning
        learning rate
        regularier
        dropout
        batch normalization
    save/load
    compile
        optimizer
        loss
        metric

hongik_2020's People

Contributors

dhrim avatar jinmkim avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.