A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
R. Doriguzzi-Corin, S. Millar, S. Scott-Hayward, et al.
Lucid is a lightweight CNN-based DDoS detection system that matches state-of-the-art accuracy with a 40x reduction in processing time, suitable for resource-constrained environments.
Mohsin Munir, Shoaib Ahmed Siddiqui, Andreas Dengel, et al.
DeepAnT uses a CNN-based predictor and unsupervised anomaly detector to detect point, contextual, and discord anomalies in time series without requiring labeled data.
Athanasios Voulodimos, Nikolaos Doulamis, Anastasios Doulamis, et al.
This review surveys deep learning methods for computer vision, covering CNNs, DBMs, DBNs, and SDAEs, their history, structure, applications, and future directions.
Konstantinos Kamnitsas, Christian Ledig, Virginia Newcombe, et al.
A dual-pathway 3D CNN with dense training and fully connected CRF achieves state-of-the-art brain lesion segmentation across multiple pathologies.
Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton
AlexNet achieved state-of-the-art image classification on ImageNet using a deep CNN with 60M parameters, ReLU, GPU training, and dropout.
Amin Ghiasi, Hamid Kazemi, Eitan Borgnia, et al.
This paper investigates the internal mechanisms of Vision Transformers, revealing their spatial information preservation, last-layer pooling behavior, and reliance on background features compared to CNNs.
Unknown
DocFormer introduces an encoder-only transformer with a CNN backbone that fuses visual, textual, and spatial features via a novel multi-modal self-attention layer for document understanding.
Unknown
Faster R-CNN introduces a Region Proposal Network (RPN) that shares convolutional features with the detection network, enabling near real-time object detection.
Unknown
MobileViT introduces a lightweight vision transformer that combines CNN and ViT strengths for efficient mobile deployment.
Zixiang Chen, Yihe Deng, Yue Wu, et al.
This paper formally proves that Mixture-of-Experts layers provably improve test accuracy over a single expert in two-layer CNNs.
Karim Abbasi, Parvin Razzaghi, Antti Poso, et al.
DeepCDA uses LSTM and CNNs with adversarial domain adaptation to predict compound-protein binding affinity across different data distributions.
Oludare Isaac Abiodun, Muhammad Ubale Kiru, Aman Jantan, et al.
A comprehensive review of ANN applications to pattern recognition, highlighting current models like GAN, CNN, and Transformer, and identifying unresolved challenges such as whimsical orientation and neuron behavior analysis.