REVIEW 9 cited by
TKAN: Temporal Kolmogorov-Arnold Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recurrent Neural Networks (RNNs) have revolutionized many areas of machine learning, particularly in natural language and data sequence processing. Long Short-Term Memory (LSTM) has demonstrated its ability to capture long-term dependencies in sequential data. Inspired by the Kolmogorov-Arnold Networks (KANs) a promising alternatives to Multi-Layer Perceptrons (MLPs), we proposed a new neural networks architecture inspired by KAN and the LSTM, the Temporal Kolomogorov-Arnold Networks (TKANs). TKANs combined the strenght of both networks, it is composed of Recurring Kolmogorov-Arnold Networks (RKANs) Layers embedding memory management. This innovation enables us to perform multi-step time series forecasting with enhanced accuracy and efficiency. By addressing the limitations of traditional models in handling complex sequential patterns, the TKAN architecture offers significant potential for advancements in fields requiring more than one step ahead forecasting.
Forward citations
Cited by 9 Pith papers
-
KANEL\'E: Kolmogorov-Arnold Networks for Efficient LUT-based Evaluation
Quantized, pruned Kolmogorov-Arnold Networks can be compiled directly into FPGA lookup tables, achieving extreme latency/resource reductions and matching state-of-the-art LUT-based networks on several benchmarks.
-
Watermarking Kolmogorov-Arnold Networks for Emerging Networked Applications via Activation Perturbation
DCT-AW embeds a watermark into KAN layer-0 activation outputs via a discrete cosine transform perturbation, and a trained detector still recovers it after fine-tuning, pruning, and retraining.
-
Improving Memory Efficiency for Training KANs via Meta Learning
MetaKANs generates each KAN activation function from a shared prompt-conditioned meta-learner, cutting trainable parameters toward MLP level while retaining comparable or better accuracy on tested benchmarks.
-
Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks
QKANs show strong empirical performance on regression, vision, and language tasks, but the claimed exponential parameter reduction is not rigorously established.
-
Toroidal area-preserving parameterizations of genus-one closed surfaces
Four Riemannian optimization algorithms (projected/Riemannian gradient and conjugate gradient) are proposed to compute toroidal area-preserving parameterizations by minimizing stretch energy on a power manifold of ring tori.
-
TFKAN: Time-Frequency KAN for Long-Term Time Series Forecasting
TFKAN places Kolmogorov-Arnold Networks directly on FFT coefficients alongside a time-domain KAN branch, improving long-term forecast accuracy on seven benchmark datasets.
-
Capsule-ConvKAN: A Hybrid Neural Approach to Medical Image Classification
A hybrid Capsule-ConvKAN model reports 91.21% accuracy on histopathological image classification, outperforming CNN, CapsNet, and ConvKAN baselines on a single dataset.
-
Localized Weather Prediction Using Kolmogorov-Arnold Network-Based Models and Deep RNNs
KAN achieves R2 up to 0.9998 for daily temperature in Abidjan and Kigali, but missing split details and baselines make the result unverifiable and likely inflated.
-
SigGate: Enhancing Recurrent Neural Networks with Signature-Based Gating Mechanisms
A signature-based forget/reset gate that ignores the hidden state yields small and task-dependent R2 changes on two crypto forecasting tasks, not the consistent improvement claimed.
Discussion (0). Continue with ORCID to comment.