RDMA Explained: The Backbone of High-Performance Computing
Learn how RDMA boosts networking speed and efficiency for high-performance and cloud applications.
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.
Automated metrics for evaluating the quality of text generation
Follow this blog post to learn about several of the best metrics used for evaluating the quality of generated text, including: BLEU, ROUGE, BERTscore, METEOR, Self-BLEU, and Word Mover’s Distance.
Data Parallelism: From Basics to Advanced Distributed Training
Understand data parallelism from basic concepts to advanced distributed training strategies in deep learning. Ideal for beginners and practitioners.
Understanding Feedforward and Feedback Networks (or recurrent) neural network
Explore the key differences between feedforward and feedback neural networks, how they work, and where each type is best applied in AI and machine learning.
How to Use MCP with OpenAI Agents
Learn how to use the Model Context Protocol with OpenAI Agents to increase tool integration, streamline workflows, and build capable AI systems.
LangSmith Explained: Debugging and Evaluating LLM Agents
Debug, trace, and evaluate LLM agents with LangSmith. Learn how LangSmith improves the reliability, observability, and performance of AI applications.
Padding In Convolutional Neural Networks
In this article, we explore how and why we use padding in CNNs in computer vision tasks. We’ll then jump into a full coding demo showing the utility of padding.
ReFT: Representation Finetuning for Language Models
In this article we introduce pyreft, a novel fine-tuning method called Representation Fine-Tuning (ReFT), which offers superior efficiency and interpretability compared to state-of-the-art methods like PEFTs.
How to train and use a custom YOLOv7 model
We examine YOLOv7 & its features, learn how to prepare custom datasets for the model, and then build a YOLOv7 demo from scratch using NBA footage.
