Another interesting type of non-linearity is the ReLU function, which sets any negative neuron output to zero. In a fully…
ARTIFICIAL INTELLIGENCE (15) – Deep learning (13) Understanding Backpropagation (1)
The issue with backpropagation is that it acts as a “leaky abstraction.” Calling backpropagation a leaky abstraction means that, although…
ARTIFICIAL INTELLIGENCE (14) – Deep learning (12) Running and Debugging a Deep Learning Project in Visual Studio Code
This article is a Step‑by‑Step Guide of how Running and Debugging a Deep learning Model/Project in Visual Studio Code. Install…
ARTIFICIAL INTELLIGENCE (13) – Deep learning (11) Understanding Decision Thresholds: Why “High” and “Low” Thresholds Matter
In many machine‑learning models—especially logistic regression—we make predictions that look like a score between 0 and 1. This score can…
ARTIFICIAL INTELLIGENCE (12) – Deep learning (10) Why Only the First Layer of a CNN Can Be Visualised as an RGB Image
Convolutional Neural Networks (CNNs) are made of many layers stacked together, each transforming the input image into more abstract representations.…
ARTIFICIAL INTELLIGENCE (11) – Deep learning (9) The Night of the Sigmoid Curve
A gentle horror story about a friendly function that turns fear into probabilities. On a foggy night, in a valley…
yolandamuriel.com 
Debe estar conectado para enviar un comentario.