intTypePromotion=1
zunia.vn Tuyển sinh 2024 dành cho Gen-Z zunia.vn zunia.vn
ADSENSE

Bài giảng Máy học nâng cao: Artificial neural network - Trịnh Tấn Đạt

Chia sẻ: Minh Vũ | Ngày: | Loại File: PDF | Số trang:62

39
lượt xem
4
download
 
  Download Vui lòng tải xuống để xem tài liệu đầy đủ

Bài giảng "Máy học nâng cao: Artificial neural network" cung cấp cho người học các kiến thức: Introduction, perceptron, neural network, backpropagation algorithm. Mời các bạn cùng tham khảo nội dung chi tiết.

Chủ đề:
Lưu

Nội dung Text: Bài giảng Máy học nâng cao: Artificial neural network - Trịnh Tấn Đạt

  1. Trịnh Tấn Đạt Khoa CNTT – Đại Học Sài Gòn Email: trinhtandat@sgu.edu.vn Website: https://sites.google.com/site/ttdat88/
  2. Contents  Introduction  Perceptron  Neural Network  Backpropagation Algorithm
  3. Introduction ❖ What are artificial neural networks?  A neuron receives a signal, processes it, and propagates the signal (or not)  The brain is comprised of around 100 billion neurons, each connected to ~10k other neurons: 1015 synaptic connections  ANNs are a simplistic imitation of a brain comprised of dense net of simple structures  Origins: Algorithms that try to mimic the brain  Very widely used in 80s and early 90s; popularity diminished in late 90s.  Recent resurgence: State-of-the-art technique for many applica1ons
  4. Comparison of computing power  Neural networks are designed to be massively parallel  The brain is effectively a billion times faster
  5. Applications of neural networks
  6. Medical Imaging
  7. Fake Videos
  8. Conceptual mathematical model  Receives input from sources  Computes weighted sum  Passes through an activation function  Sends the signal to m succeeding neurons
  9. Artificial Neural Network  Organized into layers of neurons  Typically 3 or more: input, hidden and output  Neural networks are made up of nodes or units, connected by links  Each link has an associated weight and activation function
  10. Perceptron  Simplified (binary) artificial neuron
  11. Perceptron  Simplified (binary) artificial neuron with weights
  12. Perceptron  Simplified (binary) artificial neuron; no weights
  13. Perceptron  Simplified (binary) artificial neuron; add weights
  14. Perceptron  Simplified (binary) artificial neuron; add weights
  15. Introducing Bias  Perceptron needs to take into account the bias o Bias is just like an intercept added in a linear equation. o It is an additional parameter in the Neural Network which is used to adjust the output along with the weighted sum of the inputs to the neuron. o Bias acts like a constant which helps the model to fit the given data
  16. Sigmoid Neuron  The more common artificial neuron
  17. Sigmoid Neuron  In effect, a bias value allows you to shift the activation function to the left or right, which may be critical for successful learning.  Consider this 1-input, 1-output network that has no bias:  Here is the function that this network computes, for various values of w0:
  18. Sigmoid Neuron  If we add a bias to that network, like so: Having a weight of -5 for w1 shifts the curve to the right, which allows us to have a network that outputs 0 when x is 2.
  19. Simplified Two-Layer ANN One hidden layer
  20. Simplified Two-Layer ANN
ADSENSE

CÓ THỂ BẠN MUỐN DOWNLOAD

 

Đồng bộ tài khoản
2=>2