#deep learning
Deep Learning: 26 AI articles covering deep learning news, analysis, and research
Articles
Deep Learning Automates Parameter Extraction for 2D Transistors:⭐9
Deep learning automates 2D transistor parameter extraction, boosting speed and consistency for nanoscale semiconductor characterization and modeling.
The Sigmoid Function: From 'e' to Neural Networks⭐9
Learn how the sigmoid function maps inputs to probabilities, its derivation from odds, and its role in neural networks.
Neural Networks Explained: What They Are and How to Build One in⭐10
Learn what neural networks are and how to build one from scratch in Python using NumPy, explained simply for beginners.
Backpropagation Explained for Beginners (Part 3): How⭐9
Learn how backpropagation really works in neural networks, explained simply with chain rule gradients, shared derivatives, and step-by-step examples for beginne...
Variational Autoencoders (VAEs) Explained: From Theory to ELBO⭐9
Discover how Variational Autoencoders (VAEs) work, from theory to ELBO and the reparameterization trick, explained clearly for machine learning enthusiasts.
SPP-Net Paper Walkthrough: Breaking the Fixed-Size Constraint⭐10
Learn how SPP-Net removes the fixed-size input constraint in CNNs, enabling variable image sizes without cropping or warping, with a PyTorch implementation guid...
IMDb Sentiment Analysis with DistilBERT LoRA, TF-IDF Baselines,⭐9
Explore IMDb sentiment analysis with DistilBERT LoRA, TF-IDF baselines, calibration, robustness tests, and semi-supervised learning.
Advancing Utility Pole and Sign Detection Through Deep Learning⭐10
Deep learning detects utility poles and signs from street imagery, estimating lean angles with 90% mAP via modified DETR, outperforming standard detectors.
GPU-Accelerated Differentiable Framework Resolves Speed-Accuracy⭐8
A GPU-accelerated differentiable framework from Duke and Synopsys speeds up switching power analysis without sacrificing accuracy, resolving the speed-accuracy ...
Chip Bridges Neuromorphic and Deep-Network Computing (TU Dresden)⭐9
TU Dresden unveils hybrid chip merging neuromorphic and deep-network computing, enabling energy-efficient AI with dynamic switching between spiking and neural n...