Convolutional Neural Networks: Architecture, Mechanics, and Early Applications
To address the excesive parameter counts incurred by fully connected networks when processing images—where even small images can lead to hundreds of millions of parameters—convolutional neural networks (CNNs) were introduced. CNNs exploit two key structural inductive biases: translation invariance and locality. These enable_sparse, weight-share ...
Posted on Wed, 23 Sep 2026 16:13:35 +0000 by forced4
Lightweight CNN Architectures: SqueezeNet and SqueezeNext
SqueezeNet Model SqueezeNet represents a significant advancement in lightweight neural network design, published at ICLR 2017. This architecture achieves AlexNet-level accuracy while utilizing only 1/50th of its parameters. The core innovation of SqueezeNet is the Fire Module, which consists of Squeeze and Expand components. The Squeeze compone ...
Posted on Sat, 29 Aug 2026 16:29:51 +0000 by Raphael diSanto
Fundamentals of Deep Learning
PyTorch Model Training Demo Code
In PyTorch, model training typically involves several key steps: defining the model, defining the loss function, selecting an optimizer, preparing a data loader, and writing the training loop. Below is a simple PyTorch model training demo code that implements a basic neural network for handwritten digit recognit ...
Posted on Mon, 06 Jul 2026 16:54:45 +0000 by nokicky
Surface Crack Detection with CNN on Kaggle
1. Dataset Acquisition
Concrete surface cracks are a primary defect in civil structures. Building inspection is performed to evaluate stiffness and tensile strangth. Crack detection plays a vital role in building health assessment.
The dataset contains images of various concrete surfaces with and without cracks. The image data is divided into t ...
Posted on Thu, 11 Jun 2026 17:53:30 +0000 by Jedi Legend
Understanding Convolution in Deep Learning: From Mathematics to Implementation
Convolution is a foundational operation in deep learning—especially in computer vision—where it enables hierarchical feature extraction through localized, parameter-shared transformations. Unlike general matrix multiplication, convolution exploits spatial locality and translation invariance, making it both computationally efficient and semantic ...
Posted on Mon, 08 Jun 2026 16:24:13 +0000 by puja
MobileFormer: Efficient Hybrid Architecture for Local-Global Feature Fusion
MobileFormer introduces a novel architecture that synergistically combines the strengths of convolutional neural networks (CNNs) and Transformers to achieve high efficiency with minimal computational overhead. By leveraging a lightweight bidirectional bridge between a mobile backbone and a compact Transformer, it enables effective exchange of l ...
Posted on Wed, 20 May 2026 20:19:31 +0000 by n00854180t