Deep Learning · Computer Vision · Foundations

Where neural networks meet clear explanations.

In-depth articles on deep learning foundations, optimization, and computer vision — built for practitioners who want the intuition and the math.

Topics at a glance
The map of what's here
Hover a branch to trace it. Click any article node to open it.
Radial tree — deterministic layout
Writing
Latest articles
View all topics →
Neural Networks

Activation Functions

The non-linear ingredient that makes deep learning possible. ReLU, Sigmoid, Tanh, Softmax — what they do and when to use each.

10 min read
Training

Optimization Techniques

Feature scaling, batch norm, momentum, RMSProp, Adam, and LR decay — from first principles to production practice.

12 min read
Generalization

Regularization Techniques

Stop your network memorizing noise. L1, L2, Dropout, and Early Stopping — how each works and when to combine them.

13 min read
Computer Vision

Transfer Learning for CIFAR-10

A frozen EfficientNetB0 backbone at 87–89% accuracy in under 3 minutes. Feature caching and classifier-head design.

15 min read
Generalization

Data Augmentation

Expand your dataset with flips, crops, and color jitter — plus modern approaches like MixUp and CutMix.

11 min read
Computer Vision

AlexNet Paper Walkthrough

A deep dive into Krizhevsky et al. (2012) — the architecture that won ImageNet and kicked off the deep learning era.

12 min read
Stay updated

New articles, in your inbox

Occasional posts on deep learning and computer vision. No spam.

EG

Egi Gjineci

AI/ML Engineer at Credins Bank

Tirana, Albania