A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Gokul Yenduri, M. Ramalingam, G. Chemmalar Selvi, et al.
A comprehensive review of GPT covering architecture, training, enabling technologies, applications, challenges, and future directions.
Tianyu Gu, Kang Liu, Brendan Dolan-Gavitt, et al.
This paper demonstrates that outsourced training of deep neural networks introduces security risks where adversaries can create backdoored networks that perform well on normal inputs but fail on attacker-chosen inputs.
Alvin Rajkomar, Eyal Oren, Kai Chen, et al.
Proposes a deep learning approach using raw EHR data in FHIR format to accurately predict multiple clinical outcomes across hospitals without site-specific harmonization.
Jiawei Su, Danilo Vasconcellos Vargas, Kouichi Sakurai
Proposes a black-box one-pixel attack using differential evolution that fools DNNs by modifying a single pixel, achieving 67.97% success on CIFAR-10.
Takeru Miyato, Shin‐ichi Maeda, Masanori Koyama, et al.
Virtual Adversarial Training (VAT) regularizes models by enforcing local smoothness of the label distribution via a computationally efficient, label-free adversarial direction, achieving state-of-the-art semi-supervised learning on SVHN and CIFAR-10.
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.
Bozheng Dou, Zailiang Zhu, Ekaterina Merkurjev, et al.
This review summarizes machine learning and deep learning solutions for small data challenges in molecular science, covering both basic and advanced techniques.
Paul Bergmann, Kilian Batzner, Michael Fauser, et al.
Introduces MVTec AD, a comprehensive dataset with 5354 high-resolution images across 15 categories for unsupervised anomaly detection, and benchmarks state-of-the-art methods.
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.
Ichiro Tsuda, Edgar Koerner, Hideki Shimizu
This paper presents an asynchronous neural network model with field-effect feedback that enables unsupervised learning and deterministic chaotic successive memory recall.
Kai Olav Ellefsen, Jean-Baptiste Mouret, Jeff Clune
This paper shows that evolving modular neural networks with connection costs reduces catastrophic forgetting, enabling faster learning of new skills while retaining old ones.
Jordan Pollack, Alan Blair
This paper demonstrates that simple hillclimbing with relative fitness can train a neural network to play backgammon at a competitive level, challenging the necessity of temporal difference learning.