Save this video free

Lecture 16: Artifical neuron

Burton Ma · 52:06 · Watch on YouTube

Part of Queen's University CISC 371. See all 17 lectures and search them

These notes were made with YouTube Collector. Paste any YouTube link and get the same: a summary, chapters and a searchable transcript.

Overview

Burton Ma explains an artificial neuron as a weighted sum of inputs, including a bias, followed by an activation function, then derives how its weights can be optimized with gradient descent. He applies the method to classify 150 Iris specimens as Iris setosa or not using sepal length and width, with MATLAB code that uses a surrogate derivative for the Heaviside activation to learn a separating line.

Key takeaways

Chapters

0:00 Artificial Neurons as Simple Mathematical Functions
4:00 Input Weights, Bias, and the Transfer Function
10:00 Why Neurons Need Nonlinear Activation Functions
13:00 Sigmoid, Tanh, and ReLU Activation Tradeoffs
18:00 Heaviside and Identity Activations for Optimization
22:00 Binary Classification and Labeled Training Examples
27:00 Least-Squares Loss and the Single-Neuron Gradient
37:00 Batch Gradient Descent and the Iris Setosa Task
42:00 Preparing Iris Measurements in MATLAB
47:00 Vectorized Heaviside Training Learns a Separating Line

Keep these chapters and the full searchable transcript in your own library.

Transcript excerpt

0:01 All right, good morning. Um, today's lecture um is about uh the neurons in an artificial network. Uh, so if you don't know how neur how a neural network works um uh I guess it's sufficient for you uh for you to know that an artificial network is made up of a bunch of neurons. uh each neuron is absurdly simple which you'll see today. Um so a neuron is just a kind of unit that computes uh some value given a vector of inputs. Uh so in other words a neuron is just a function. Uh and that's literally all it is. Um so it's inspired from biology. So the first model of an artificial neuron or an early model of the artificial neuron was somewhere in

0:48 the 50s um where someone came up with what's called the perceptron algorithm. um the neurons we use today are not much changed from then. Um so the big differences that have happened since the 50s is our ability to arrange neurons into large networks uh and to be able to train them uh effectively. Uh and so that uh I guess being able to train an artificial neuronet network was uh what won uh the Nobel Prize in physics um for uh Hinton. I can't remember the other two off the top of my head. Um uh but it's kind of a big deal uh as I'm sure you're all aware right now.

1:36 Okay. So this lecture we're going to talk about the structure of the neuron. You're going to see it's very simple. Um it basically describes a mathematical function. Um we're going to compute its gradient uh so that we can actually um optimize something uh using one of these neurons. Um so we're going to train a single

This is the start of the transcript. Save this video free for the whole transcript, searchable and time-coded.

In this course

Related notes

Summary, takeaways, and chapters were generated by AI from the video's transcript and may contain errors. The video belongs to its creator, Burton Ma.

Want the full transcript?

Save this video in YouTube Collector to get its complete searchable transcript, your own AI summaries, and a library that keeps every video you collect in one place.