admin管理员组文章数量:1566222
- [1. Introduction — Dive into Deep Learning 1.0.0-beta0 documentation](https://d2l.ai/chapter_introduction/index.html#fig-wake-word) #[[Roam-Highlights]]
# [1. Introduction](https://d2l.ai/chapter_introduction/index.html#introduction)
- an interface - database engine - conceivable circumstance - every possible corner case - not be worrying about machine learning - a pattern that changes over time - a changing world
## 1.1 A Motivating Example[¶](https://d2l.ai/chapter_introduction/index.html#a-motivating-example)
- ==**In other words**==, even if you do not know how to program a computer to recognize the word “Alexa”, you yourself are able to recognize it.
- a flexible program whose behavior is determined by a number of ==parameters==
- think of the parameters as ==knobs== that we can turn, manipulating the behavior of the program
- we call the program a ==model==
- The set of all distinct programs (input-output mappings) that we can produce
- is called a ==family== of models
- the meta-program that uses our dataset to choose the parameters is called a ==learning algorithm==
- our model receives a snippet of audio as ==input==, and the model generates a selection among {yes, no}as output.
- the ==learning== is the process by which we discover the right setting of the knobs coercing the desired behavior from our model
- Grab some of your data (e.g., audio snippets and corresponding{yes, no} labels)
- ==**To summarize**==, rather than code up a wake word recognizer, we code up a program that can _learn_ to recognize wake words, if presented with a large labeled dataset.
- eventually learn to emit a very large positive number if it is a cat, a very large negative number if it is a dog, and something closer to zero if it is not sure.
- ==Deep learning==, which we will explain in greater detail later, is just one among many popular methods for solving machine learning problems.
- Fig. 1.1.1 Identify a wake word.[¶](https://d2l.ai/chapter_introduction/index.html#id49 "Permalink to this image")
- Fig. 1.1.2 A typical training process.[¶](https://d2l.ai/chapter_introduction/index.html#id50 "Permalink to this image")
# [1.2 Key Components](https://d2l.ai/chapter_introduction/index.html#key-components)
- [1. Introduction — Dive into Deep Learning 1.0.0-beta0 documentation](https://d2l.ai/chapter_introduction/index.html#key-components) #[[Roam-Highlights]]
版权声明:本文标题:2023春 - 神经网络与深度学习 - 笔记1 内容由热心网友自发贡献,该文观点仅代表作者本人, 转载请联系作者并注明出处:https://www.elefans.com/dongtai/1726616717a1078272.html, 本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容,一经查实,本站将立刻删除。
发表评论