吴恩达深度学习笔记1-Course1-Week1【深度学习概论】
2018.5.7
吳恩達(dá)深度學(xué)習(xí)視頻教程網(wǎng)址
網(wǎng)易云課堂:https://mooc.study.163.com/smartSpec/detail/1001319001.htm
Coursera:https://www.coursera.org/learn/neural-networks-deep-learning
PS:網(wǎng)易云上不提供測(cè)驗(yàn)和作業(yè),Cousera上有。
深度學(xué)習(xí)概論:
本篇主要關(guān)于深度學(xué)習(xí)的一些介紹和幾個(gè)相關(guān)的術(shù)語
Single/Multiple neural network:
深度學(xué)習(xí)的本質(zhì): Given data (input and output) and fit a function that will predict output.
修正線性單元:(Rectified Linear Unit –ReLU)一種人工神經(jīng)網(wǎng)絡(luò)中常用的激活函數(shù)(activation function)
卷積神經(jīng)網(wǎng)絡(luò): Convolution Neural Network (CNN) used often for image application
循環(huán)神經(jīng)網(wǎng)絡(luò): Recurrent Neural Network (RNN) used for one-dimensional sequencedata such as translating English to Chinses or a temporal component such astext transcript.
結(jié)構(gòu)化數(shù)據(jù): Structured data refers to things that has a defined meaning such as price, age
非結(jié)構(gòu)化數(shù)據(jù): Unstructured data refers to thing like pixel, raw audio, text.
深度學(xué)習(xí)三要素: large amount of data available with label, fast computation and neural network algorithm.
Two things have to be considered to get to the high level of performance:
1. Being able to train a big enough neural network
2. Huge amount of labeled data
訓(xùn)練神經(jīng)網(wǎng)絡(luò)是一個(gè)迭代過程: Idear–Code–Experiment
It could take a good amount of time to train a neural network, which affects your productivity. Faster computation helps to iterate and improve new algorithm.
總結(jié)
以上是生活随笔為你收集整理的吴恩达深度学习笔记1-Course1-Week1【深度学习概论】的全部?jī)?nèi)容,希望文章能夠幫你解決所遇到的問題。
- 上一篇: 建筑学跨专业计算机考研方向,不适合女生报
- 下一篇: 吴恩达深度学习笔记13-Course4-