EvoClass
PolyU COMP5511 • Lab 7
The Connectionist Engine (Deep Learning & CNNs)
The Limits of Classic ML
Last Week:
We used an SVM. We had to manually "flatten" the image, destroying all spatial information (e.g., which pixel is next to which).
The Problem:
If you shift a digit one pixel to the left, the flattened 784-number array looks completely different to the SVM!
The Solution:
Deep Learning
. We will build a Neural Network that looks at 2D images directly and learns its own features.
1D Flattened Array vs 2D Spatial Grid
Open Colab Notebook
Session
Lab 7
Date
2026-03-02
Instructor
Ran Cheng
Duration
60 Mins
