DeepLearning W1-Introduction
DeepLearning W1-Introduction
Introduction
Analyze the major trends driving the rise of deep learning, and give examples of where and how it is applied today.
学习目标
- Discuss the major trends driving the rise of deep learning.
- Explain how deep learning is applied to supervised learning
- List the major categories of models (CNNs, RNNs, etc.), and when they should be applied
- Assess appropriate use cases for deep learning
What is a Neural Network?
Supervised Learning with Neural Networks
- 定义:
- 由训练资料中学到或创建一个模式(函数 / learning model),并依此模式推测新的实例
- neural networks
- RNN (Recurrent Neural Network) 适用于:
- sequence data,for example:
- language translate
- CNN(convolutional neural networks)
Why is Deep Learning taking off?
scale drives deep learning progress
Influencing Factors(影响因素)
- Data
- Computation
- Algorithms
- 类型
- Sigmoid激活函数(图一)
- ReLU激活函数(图二)
- stands for Rectified Linear Unit
- 对比
- switching from sigmoid to ReLU activation functions allows faster training
- 类型
相关资料
This post is licensed under CC BY 4.0 by the author.