Aprendizaje profundo: arquitecturas avanzadas y entrenamiento eficiente en GPU

Resumen

Master advanced deep learning architectures and efficient training techniques using PyTorch Lightning, timm, ConvNeXt, Vision Transformers, RoPE, SwiGLU, RMSNorm, and Weights & Biases. This course equips you to design, train, and benchmark modern backbones on limited GPU hardware for real-world production use.

Module 1 introduces modern backbone architectures, tracing the evolution from ResNets to ConvNeXt and Vision Transformers, covering patch embeddings, multi-head self-attention, and position encodings. Module 2 dives into training dynamics and stabilization techniques including RMSNorm, SwiGLU activations, and Rotary Position Embeddings (RoPE) for stable, scalable training.

Module 3 focuses on efficient training on limited GPUs using mixed precision (FP16/BF16), gradient accumulation, efficient data pipelines, and distributed training with DDP/FSDP in Lightning. Module 4 covers experiment tracking with TensorBoard and W&B, profiling FLOPs and throughput, and a hands-on ViT vs.

CNN Showdown project with fine-tuning in timm. By the end of this course, you will:

- Build and fine-tune ConvNeXt and Vision Transformer backbones using PyTorch Lightning and timm - Apply RMSNorm, SwiGLU, and RoPE to stabilize and scale deep transformer training - Implement mixed precision, gradient accumulation, and DDP/FSDP for efficient multi-GPU training - Design controlled CNN vs.

ViT experiments with W&B tracking and PyTorch profiling Disclaimer:

This is an independent educational resource created by Board Infinity for informational and educational purposes only. This course is not affiliated with, endorsed by, sponsored by, or officially associated with any company, organization, or certification body unless explicitly stated.

The content provided is based on industry knowledge and best practices but does not constitute official training material for any specific employer or certification program. All company names, trademarks, service marks, and logos referenced are the property of their respective owners and are used solely for educational identification and comparison purposes.

Programa

• Arquitecturas Modernas de Backbone (ConvNeXt y Vision Transformers)
Explora la evolución de los backbones de aprendizaje profundo desde los CNN clásicos hasta ConvNeXt y Vision Transformers, comprendiendo su mecánica, compensaciones y relevancia en la industria.
• Dinámicas de Entrenamiento y Técnicas de Estabilización
Aprende técnicas modernas de estabilización y eficiencia, incluidas RMSNorm, activaciones SwiGLU y Embeddings de Posición Rotativa que impulsan los transformers de última generación.
• Entrenamiento Eficiente con GPUs Limitadas
Domina técnicas prácticas para entrenar modelos grandes en hardware limitado, incluyendo precisión mixta, acumulación de gradientes y estrategias de entrenamiento distribuido.
• Experimentación, Seguimiento y Proyecto de Enfrentamiento ViT vs CNN
Aprende a rastrear experimentos profesionalmente y aplica todos los conceptos del curso en un proyecto práctico de Enfrentamiento ViT vs CNN utilizando ajuste fino con timm y PyTorch Lightning.

---

Impartido por

Board Infinity

---

Materias

Computer Science