Reinforcement Learning Environments
‘ In this article, we explore why reinforcement learning environments are worth knowing about and implement sky-rl on the cloud provider.’
Advanced Recurrent Neural Networks: Bidirectional RNNs
This series gives an advanced guide to different recurrent neural networks (RNNs). You will gain an understanding of the networks themselves, their architectures, their applications, and how to bring the models to life using Keras.
YOLOv10: Advanced Real-Time End-to-End Object Detection (Detailed Guide)
In this article we will explore YOLOv10: The latest in real-time object detection. With improved post-processing and model architecture, YOLOv10 achieves state-of-the-art performance.
Parameter-Efficient Fine-Tuning with LoRA Using Custom Data
‘Learn how to fine-tune LLMs using LoRA for custom domains. This step-by-step guide explains parameter-efficient fine-tuning using a custom dataset.’
Visual Agentic Intelligence with Kimi K2.5
Learn about Kimi K2.5’s performance breakthroughs and how to deploy the model on GPU cloud servers.
OmniGen2 – a Powerful Image Editing Model
In this tutorial, show how to run and use the new Omnigen2 model on a GPU Droplet and their custom Gradio application.
Writing ResNet from Scratch in PyTorch
In this continuation on our series of writing DL models from scratch with PyTorch, we learn how to create, train, and evaluate a ResNet neural network for CIFAR-100 image classification.
Post-training Agentic Models: Kimi K2
‘This article discusses post-training Kimi K2, a 1T parameter open-weight MoE model designed for agentic use. The goal is to make the technical report more digestible for those interested in learning about how Kimi K2 was post-trained.’
SAM 2: Meta’s Next-Gen Model for Video and Image Segmentation
In this article, we will explore SAM 2, which expands the capabilities of the original SAM to handle both images and videos. It excels in real-time object segmentation, enabling dynamic interaction through prompts and memory attention.
A Review of Popular Deep Learning Architectures: AlexNet, VGG16, and GoogleNet
This review explores three foundational deep learning architectures—AlexNet, VGG16, and GoogleNet—that have significantly advanced the field of computer vision.
