Save this video free

Lecture 17: Artifical neuron (cont); Linear neural network

Burton Ma · 50:23 · 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 reviews training a single artificial neuron on Fisher's Iris data, showing how MATLAB vectorization computes least-squares gradients and how learned weights define a linear decision boundary. He then builds toward backpropagation in a four-layer network, defining layer and weight notation, deriving the output-neuron gradient by the chain rule, and connecting small activation derivatives to vanishing gradients.

Key takeaways

Chapters

0:00 Binary Iris Classification with a Single Neuron
3:00 Vectorizing the Single-Neuron Gradient in MATLAB
9:00 Gradient Descent Learns an Iris Decision Boundary
14:00 Sigmoid Outputs and Binary Classification Thresholds
19:00 From One Neuron to a Four-Layer Network
22:00 Input, Hidden, and Output Layers in Network Diagrams
26:00 Bias Units, Activations, and Network Connections
31:00 Sink-Source Weight Indices and Bias Notation
35:00 Training Samples, Residuals, and Least-Squares Cost
43:00 Chain-Rule Gradients and the Vanishing-Gradient Issue

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

Transcript excerpt

0:01 All right, good morning everybody. Uh so this let me quickly remind you of what we were talking about in the last class. So in the last class we were looking at a single artificial neuron. Uh we computed the gradient of the neuron. Uh and then we wanted to train the neuron on a sing in a simple binary classification task. So in the binary classification task you're trying to separate two groups of data. You're trying to separate groups of data into one of two different classes. Uh and so the example we were looking at uh here was the uh iris data from um uh from Fisher's. Fisher was a statistician. Um So when you plot the iris data here you can see there's clearly two different classes, right? There's the blue and the red. We want to train a neuron so that it can

0:48 distinguish between these two um uh these two classes, right? So in other words, if we feed a neuron one of these data points, so this is like 5.5, 4.4. We feed that input into a neuron, it should spit out uh this is setosa, so it should spit out a one. Right? So the our neuron outputs a one if it's a the species of the uh sample is setosa. Or if it thinks the species is setosa, and it spits out a zero if it if it thinks the species is something else. Okay, so to train this thing uh we want to minimize the um sum of some objective function. And we chose a least squares objective function. Uh so to do that we uh it's a non-linear problem cuz the neuron is a not represents a non-linear function.

1:37 So we need some sort of um minimization algorithm, right? There's

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.