程序代写代做代考 deep learning algorithm Foundations of Machine Learning Neural Networks

Foundations of Machine Learning Neural Networks
Kate Farrahi
ECS Southampton
November 19, 2020
1/13

References
􏰂 Pattern Recognition and Machine Learning by Christopher Bishop
2/13

References
􏰂 Pattern Recognition and Machine Learning by Christopher Bishop
􏰂 Michael Nielson’s online book http://neuralnetworksanddeeplearning.com
2/13

References
􏰂 Pattern Recognition and Machine Learning by Christopher Bishop
􏰂 Michael Nielson’s online book http://neuralnetworksanddeeplearning.com
􏰂 Deep Learning by Ian Goodfellow, Y. Bengio, and A. Courville http://www.deeplearningbook.org
2/13

References
􏰂 Pattern Recognition and Machine Learning by Christopher Bishop
􏰂 Michael Nielson’s online book http://neuralnetworksanddeeplearning.com
􏰂 Deep Learning by Ian Goodfellow, Y. Bengio, and A. Courville http://www.deeplearningbook.org
􏰂 Step by Step Example of Backpropagation: http://mattmazur.com/2015/03/17/ a-step-by-step-backpropagation-example
2/13

References
􏰂 Pattern Recognition and Machine Learning by Christopher Bishop
􏰂 Michael Nielson’s online book http://neuralnetworksanddeeplearning.com
􏰂 Deep Learning by Ian Goodfellow, Y. Bengio, and A. Courville http://www.deeplearningbook.org
􏰂 Step by Step Example of Backpropagation: http://mattmazur.com/2015/03/17/ a-step-by-step-backpropagation-example
2/13

The Neuron
3/13

The Human Brain
􏰂 Highly complex, non-linear, and parallel ”computer”
􏰂 Structural constituents: neurons
􏰂 The structure of the brain is extremely complex and not fully understood
􏰂 Billions of nerve cells (neurons) and trillions of interconnections in the human brain
􏰂 Scientists tried to mimic the brain’s behaviour in proposing the artificial neural network (ANN)
􏰂 The human brain is the inspiration for ANNs though we cannot say ANNs actually replicate the brain’s behaviour very well, they are extremely simplified
􏰂 Great video about the brain https://www.youtube.com/watch?v=nvXuq9jRWKE
4/13

The Neuron
biological neuron
artificial neuron
5/13

The Perceptron
6/13

History of Neural Networks: McCulloch-Pitts Model
􏰂 1943 McCulloch and Pitts introduced the first model of an extremely simple artificial neuron.
􏰂 The inputs and outputs could be either a zero or a one.
􏰂 They introduced the idea of an excitatory and inhibitory
potential using weights (+/-).
􏰂 Each input is weighed and the summed activation is either transmitted (output of 1) or not (output of 0).
􏰂 The McCulloch-Pitts model lacked a mechanism for learning, which was crucial for it to be usable for AI.
􏰂 Link to the Original Paper https: //link.springer.com/article/10.1007%2FBF02478259
7/13

History of the Perceptron
􏰂 1957 Rosenblatt introduced the perceptron which was an electronic device constructed using biological principles and showed the ability to learn.
􏰂 1962 Rosenblatt wrote a book about the Perceptron and received international recognition.
􏰂 1969 Marvin Minsky and Seymour Papert published the book ”Perceptrons” which proved some limitations of the perceptron (that linear functions cannot model non-linears ones) having a big effect on the community.
8/13

History of the Perceptron
􏰂 Initially the perceptron seemed promising, but it was quickly shown that perceptrons could not be used to classify many classes of patterns.
􏰂 This caused the field of neural networks to stagnate for many years before it was recognised that a feedforward neural network with two or more layers (multilayer perceptrons) had far greater power.
􏰂 The popularity of neural networks resurged in the 1980s.
􏰂 Today deep learning is state of the art for many applications in machine learning.
9/13

The Perceptron
Source: http://www.andreykurenkov.com/writing/ai/a-brief-history-of-neural-nets-and-deep-learning/
10/13

The Perceptron Algorithm
Begin Initialize
Set all of the weights wi to small random numbers
Training
For T iterations (or until the convergence criteria is met): For each input vector xj :
Compute the activation of each neuron i:
yj =f(
wixij)=
􏰁m i=0
􏰁
m
i=0 (1) 0 otherwise

1 if wixij>0
Update each weight as follows:
wi ←wi −η(yj −tj)·xij (2)
11/13

Example
Solve the logical AND function using the perceptron algorithm.
12/13

Example
Solve the logical AND function using the perceptron algorithm. 􏰂 Givenb=1,w1 =0,w2 =0,η=0.1,findasolution
12/13

Example
Solve the logical AND function using the perceptron algorithm. 􏰂 Givenb=1,w1 =0,w2 =0,η=0.1,findasolution
􏰂 After how many iterations did the perceptron converge?
12/13

Example
Solve the logical AND function using the perceptron algorithm. 􏰂 Givenb=1,w1 =0,w2 =0,η=0.1,findasolution
􏰂 After how many iterations did the perceptron converge?
􏰂 Do you need a bias term?
12/13

Example
Solve the logical AND function using the perceptron algorithm. 􏰂 Givenb=1,w1 =0,w2 =0,η=0.1,findasolution
􏰂 After how many iterations did the perceptron converge?
􏰂 Do you need a bias term?
􏰂 What are some suitable convergence criteria?
12/13

Example
Solve the logical AND function using the perceptron algorithm. 􏰂 Givenb=1,w1 =0,w2 =0,η=0.1,findasolution
􏰂 After how many iterations did the perceptron converge?
􏰂 Do you need a bias term?
􏰂 What are some suitable convergence criteria? 􏰂 Is there more than one possible solution?
12/13

Example
Solve the logical AND function using the perceptron algorithm. 􏰂 Givenb=1,w1 =0,w2 =0,η=0.1,findasolution
􏰂 After how many iterations did the perceptron converge?
􏰂 Do you need a bias term?
􏰂 What are some suitable convergence criteria?
􏰂 Is there more than one possible solution?
􏰂 What happens if you set η to a very large number?
12/13

Example
Solve the logical AND function using the perceptron algorithm. 􏰂 Givenb=1,w1 =0,w2 =0,η=0.1,findasolution
􏰂 After how many iterations did the perceptron converge?
􏰂 Do you need a bias term?
􏰂 What are some suitable convergence criteria?
􏰂 Is there more than one possible solution?
􏰂 What happens if you set η to a very large number? 􏰂 What happens if you set η to a very small number?
12/13

Example
Solve the logical AND function using the perceptron algorithm. 􏰂 Givenb=1,w1 =0,w2 =0,η=0.1,findasolution
􏰂 After how many iterations did the perceptron converge?
􏰂 Do you need a bias term?
􏰂 What are some suitable convergence criteria?
􏰂 Is there more than one possible solution?
􏰂 What happens if you set η to a very large number? 􏰂 What happens if you set η to a very small number?
12/13

Example
Solve the logical XOR function using the perceptron algorithm.
13/13