没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
Lex Fridman
lex.mit.edu
January
2018
MIT 6.S094: Deep Learning for Self-Driving Cars
https://selfdrivingcars.mit.edu
For the full updated list of references visit:
https://selfdrivingcars.mit.edu/references
Lecture 4:
Computer Vision
Lex Fridman
lex.mit.edu
January
2018
MIT 6.S094: Deep Learning for Self-Driving Cars
https://selfdrivingcars.mit.edu
Lex Fridman
lex.mit.edu
January
2018
MIT 6.S094: Deep Learning for Self-Driving Cars
https://selfdrivingcars.mit.edu
Supervised
Learning
Unsupervised
Learning
Semi-Supervised
Learning
Reinforcement
Learning
Computer Vision is Deep Learning
References: [81]
Computer Vision
Lex Fridman
lex.mit.edu
January
2018
MIT 6.S094: Deep Learning for Self-Driving Cars
https://selfdrivingcars.mit.edu
Images are Numbers
References: [89]
• Regression: The output variable takes continuous values
• Classification: The output variable takes class labels
• Underneath it may still produce continuous values such as
probability of belonging to a particular class.
Lex Fridman
lex.mit.edu
January
2018
MIT 6.S094: Deep Learning for Self-Driving Cars
https://selfdrivingcars.mit.edu
Computer Vision with Deep Learning:
Our intuition about what’s “hard” is flawed (in complicated ways)
References: [6, 7, 11, 68]
“Encoded in the large, highly evolve sensory and motor portions of the human brain is a billion years of experience about the nature of
the world and how to survive in it.… Abstract thought, though, is a new trick, perhaps less than 100 thousand years old. We have not yet
mastered it. It is not all that intrinsically difficult; it just seems so when we do it.”
- Hans Moravec, Mind Children (1988)
Visual perception: 540,000,000 years of data
Bipedal movement: 230,000,000 years of data
Abstract thought: 100,000 years of data
Prediction: Dog
+ Distortion Prediction: Ostrich
Lex Fridman
lex.mit.edu
January
2018
MIT 6.S094: Deep Learning for Self-Driving Cars
https://selfdrivingcars.mit.edu
For the full updated list of references visit:
https://selfdrivingcars.mit.edu/references
Neuron: Biological Inspiration for Computation
• Neuron: computational building
block for the brain
[18, 143]
• (Artificial) Neuron: computational
building block for the “neural network”
Differences (among others):
• Parameters: Human brains have ~10,000,000
times synapses than artificial neural networks.
• Topology: Human brains have no “layers”.
Topology is complicated.
• Async: The human brain works
asynchronously, ANNs work synchronously.
• Learning algorithm: ANNs use gradient
descent for learning. Human brains use … (we
don’t know)
• Processing speed: Single biological neurons
are slow, while standard neurons in ANNs are
fast.
• Power consumption: Biological neural
networks use very little power compared to
artificial networks
• Stages: Biological networks usually don't stop
/ start learning. ANNs have different fitting
(train) and prediction (evaluate) phases.
Similarity (among others):
• Distributed computation on a large scale.
剩余71页未读,继续阅读
资源评论
passionSnail
- 粉丝: 456
- 资源: 7247
下载权益
C知道特权
VIP文章
课程特权
开通VIP
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- js基础但是这个烂怂东西要求标题不能少于10个字才能上传然后我其实还没有写完之后再修订吧.md
- electron-tabs-master
- Unity3D 布朗运动算法插件 Brownian Motion
- 鼎微R16中控升级包R16-4.5.10-20170221及强制升级方法
- 鼎微R16中控升级包公版UI 2015及强制升级方法,救砖包
- 基于CSS与JavaScript的积分系统设计源码
- 生物化学作业_1_生物化学作业资料.pdf
- 基于libgdx引擎的Java开发连连看游戏设计源码
- 基于MobileNetV3的SSD目标检测算法PyTorch实现设计源码
- 基于Java JDK的全面框架设计源码学习项目
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功