RunByAI

Tag: deep learning

50 post(s)

October 6, 20260 comment(s)

Introduction to Activation Function: Why Neural Networks Cannot Do Without Nonlinear Switches

If there is only matrix multiplication, even the deepest neural network will only be a large linear transformation, and it will not have complex patterns at all. What truly brings neural networks to l

Tech Guide deep learning large model

October 5, 20260 comment(s)

Introduction to Anomaly Detection: How AI Spots the Odd One Out in Data

What is anomaly detectionAnomaly detection, also called outlier detection, aims to find the samples in a large dataset that differ from the majority. Those samples may be early signs of equipment fail

Tech Guide 机器学习 deep learning

October 4, 20260 comment(s)

Introduction to Semantic Segmentation: How AI Labels Every Pixel

What is semantic segmentationSemantic segmentation assigns a class label to every pixel in an image. While classification gives one label to the whole image and object detection returns bounding boxes

Tech Guide Computer Vision deep learning

October 4, 20260 comment(s)

Introduction to Object Detection: How AI "frames" objects in the image

What is object detectionObject detection needs to answer two questions: what objects are in the picture (classification), and where they are located (localization). Localization is usually represented

Tech Guide Computer Vision deep learning

October 3, 20260 comment(s)

Introduction to Neural Architecture Search (NAS): How AI "designs" neural networks on its own

What is neural architecture searchNeural Architecture Search (NAS) refers to the use of algorithms to automatically find the "structure" of a neural network, rather than relying on manual trial and er

Tech Guide deep learning

October 2, 20260 comment(s)

Introduction to State Space Modeling (SSM) and Mamba: Another Path to Sequence Modeling Beyond Transformers

In the past few years, sequence modeling has been almost dominated by Transformers. It relies on self attention to allow each position to directly "see" all other positions, which has excellent result

Tech Guide deep learning Large Language Model (LLM)

October 2, 20260 comment(s)

Introduction to Variational Autoencoder (VAE): How Generative Models "Compress" and "Restore"

What would happen if you had a model first compress an image into a small segment of numbers, and then reconstruct the original image based solely on that segment of numbers? This is exactly the idea

Tech Guide deep learning 机器学习

October 1, 20260 comment(s)

Introduction to Graph Neural Networks (GNNs): How AI Understands "Relationships"

Images, text, and speech data are usually arranged neatly and are suitable for processing using convolution or sequence models. But in reality, there is still a large amount of "relational" data - soc

Tech Guide deep learning 机器学习

October 1, 20260 comment(s)

Introduction to Meta Learning: How AI "learns to learn"

The machine learning we are familiar with usually trains a model with a large amount of data for a specific task, and often has to start from scratch for another task. Meta Learning aims to solve this

Tech Guide deep learning 机器学习

October 1, 20260 comment(s)

Introduction to Generative Adversarial Networks (GANs): How AI Learned to Create through "Left Right Battle"

When it comes to AI generated images, many people think of diffusion models. But before the diffusion model became popular, another paradigm that profoundly influenced generative AI had already emerge

Tech Guide deep learning image generation

50 post(s)

...