arXiv:2608. 10464v1 Announce Type: new Abstract: Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory constraints.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2510. 03389v2 Announce Type: replace-cross Abstract: Current quantum computers require algorithms that use limited resources economically.
arXiv:2608. 01194v1 Announce Type: cross Abstract: Artificial intelligence has been transformed by deep neural networks, yet the search for new learning architectures continues.
arXiv:2509. 14026v2 Announce Type: replace-cross Abstract: Variational quantum circuits (VQCs) are central to quantum machine learning, while recent progress in Kolmogorov-Arnold networks (KANs) highlights the power of learnable activation functions.
arXiv:2506. 21324v3 Announce Type: replace-cross Abstract: Neuromorphic and quantum computing have recently emerged as promising paradigms for advancing artificial intelligence, each offering complementary strengths.
Hybrid Variational Quantum-Classical Framework with Adaptive Weighting and Efficiency Assessment introduces Sim‑HVQC, a hybrid deep quantum neural network that integrates an adaptive, parameter‑free SimAM weighting module with classical feature extraction to retain class‑discriminative information before encoding into a Variational Quantum Circuit. Unlike prior work limited to binary classification, this framework is trained and evaluated on multiple multi‑class datasets such as MNIST, KMNIST, Fashion‑MNIST, and EMNIST. The study highlights reproducibility, parameter efficiency, and interpretability through multi‑seed evaluation, parameter analysis, and latent/quantum feature inspection, with source code publicly available on GitHub.
The paper introduces vFedProtoQNAS, a prototype‑guided personalized quantum neural architecture search method for virtual federated learning. It allows each client to independently design and train a device‑specific quantum neural network while avoiding parameter aggregation across structurally different models. Instead, clients share class‑wise latent prototypes, which are refined using global prototypes from the server to serve as federated semantic anchors, leading to a 3.70% accuracy improvement over FedAvg.