Every series, start to finish.

Grounding DINO

Open-set object detection with language-guided grounding.

~11 min total

Mamba Transformers

State space models and the Mamba architecture.

~38 min total

4 partsAdvanced

Neural Architecture Search

Automated NAS from theory to practice with Optuna.

~54 min total

Kolmogorov-Arnold Networks

KANs as a flexible alternative to MLPs.

~24 min total

Convolutional KAN

Applying KAN principles to convolutional neural networks.

~20 min total

3 partsBeginner

YOLO Object Detection

YOLO from beginner's guide through math to full implementation.

~23 min total

Matryoshka Transformers

Matryoshka representation learning for vision-language models.

~19 min total

4 partsBeginner

Vision-Language Models

Understanding, fine-tuning, and applying VLMs with LoRA.

~91 min total

4 partsIntermediate

Diffusion Models

From DDPM's foundational math through DDIM's fast sampling, latent diffusion models, and the FLUX architecture — how modern image generation actually works.

~74 min total

3 partsIntermediate

Stable Diffusion & ControlNet

Generative image models from basics to precise control.

~31 min total

DenseNet

Densely connected convolutional networks — theory and code.

~20 min total

MobileNet

Efficient neural networks for mobile vision — overview and implementation.

~33 min total

Vision Transformers

ViT from simple guide to full implementation.

~18 min total

5 partsBeginner

Distributed Training

Scale PyTorch across GPUs with Accelerate and Fabric.

~36 min total

Kubeflow for MLOps

Machine learning pipelines on Kubernetes.

~21 min total

2 partsAdvanced

ONNX Deployment

Build and deploy computer vision models with ONNX Runtime.

~64 min total

3 partsIntermediate

Model Serving with LitServe

Deploy CV models with LitServe and Docker.

~28 min total

MLflow for ML Tracking

Experiment tracking, best practices, and CI/CD with MLflow.

~30 min total

Mixture of Experts

Sparse MoE from theory through GShard to Switch Transformer.

~32 min total

Attention Mechanisms

Transformers vs CNNs — theory and complete code guide.

~15 min total

Rust for Python Developers

Get started with Rust and build Python extension packages.

~14 min total

Python 3.14

What's new and what's changed in Python 3.14.

~9 min total

Milvus for Machine Learning

Using Milvus as a vector database for computer vision, model training, and active learning.

~94 min total

CLIP: Vision-Language Pretraining

From the original CLIP paper to a full implementation.

~48 min total

Classic CNN Architectures

A chronological deep dive into the networks that defined modern computer vision.

~46 min total

4 partsBeginner

Python for ML Engineers

Python language features every ML engineer should know — decorators, functools, itertools, and concurrency.

~54 min total

2 partsAdvanced

PyTorch Lightning

Get started with PyTorch Lightning and migrate your existing PyTorch code.

~14 min total

4 partsAdvanced

PyTorch Training Optimization

Squeeze every bit of performance out of your PyTorch training — from data loading to AMP to custom CUDA.

~39 min total

5 partsAdvanced

Inference Optimization

Make models faster at inference — quantization, edge deployment, compilation, and efficient attention.

~60 min total

Self-Supervised Learning

Training models without labels — from theory to student-teacher networks in PyTorch.

~16 min total