Welcome :)
Wi-Fi
Name: FAC
Pass:
StochasticParrots27
Materials
Discord
Starting at 18:10
The Perceptron
The Mark I Perceptron
Cornell Aeronautical Laboratory, 1960
Character recognition.
An artificial neuron
A Logical Calculus of the Ideas Immanent in Nervous Activity, McCulloch and Pitts, 1943
A weighted sum of inputs and an activation: AND, OR, NOT.
Can you explain what this diagram is showing?
The activation function
Why is the activation function needed?
Learning from experience
What would have to change for this neuron to learn?
The perceptron
The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain, Frank Rosenblatt, 1958
Adjustable weights and bias, trained on labelled examples.
What can this machine actually learn?
Weights and bias
Two parameters, two properties of the line.
Which part of the model controls which property of the line?
The prediction
Error = Expected − Prediction
What are the possible values of the error?
The update
What gets updated and in what direction?
The learning loop
The XOR limit
Where does the line go on this graph?
Layers
Three units, two layers: OR and NAND, then AND.
Could the machine have learned these weights itself?
The perceptron today
The multi-layer perceptron (MLP) inside a transformer block.
Whiteboard questions
- Draw a perceptron: inputs, weights, bias, weighted sum, activation function, and prediction.
- Draw a 2D classification problem: two feature axes, two classes, and a possible separating line.
- On the boundary, show what changing the weights does and what changing the bias does.
- Make an AND truth table, plot the four points, and draw a boundary.
- Make an XOR truth table, plot the four points, and try to draw a single boundary. Why does it fail?
Let's do it!
Machine Learning Apprenticeship
52 in-person workshops format
Fully funded funding
Peer-led discussion every session cohort
Projects tied to real work outcomes
Eligibility
Employed or own company employed
Resident for 3+ years residency