REVIEW 6 cited by
CKConv: Continuous Kernel Convolution For Sequential Data
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
Signed reviews
read the original abstract
Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizons, and must be trained sequentially. Convolutional networks are unable to handle sequences of unknown size and their memory horizon must be defined a priori. In this work, we show that all these problems can be solved by formulating convolutional kernels in CNNs as continuous functions. The resulting Continuous Kernel Convolution (CKConv) allows us to model arbitrarily long sequences in a parallel manner, within a single operation, and without relying on any form of recurrence. We show that Continuous Kernel Convolutional Networks (CKCNNs) obtain state-of-the-art results in multiple datasets, e.g., permuted MNIST, and, thanks to their continuous nature, are able to handle non-uniformly sampled datasets and irregularly-sampled data natively. CKCNNs match or perform better than neural ODEs designed for these purposes in a faster and simpler manner.
Forward citations
Cited by 6 Pith papers
-
Geometric Hyena Networks for Large-scale Equivariant Learning
Geometric Hyena is an equivariant long-convolutional architecture that captures global geometric context with sub-quadratic complexity and outperforms equivariant transformer baselines on several RNA and protein predi...
-
Quantifying Memory Utilization with Effective State-Size
Effective state-size, the rank of a causal operator submatrix, is proposed and empirically validated as a memory-utilization proxy that beats cache size at predicting recall-task accuracy and reveals how LLMs reset co...
-
STAR: Synthesis of Tailored Architectures
A hierarchical genome search over linear input-varying systems, evolved with NSGA-2, produces language model architectures that match or outperform Transformer++ and StripedMamba on quality, size, and cache efficiency.
-
Deep Loss Convexification for Learning Iterative Models
Adding star-convexity hinge losses during training makes a model's loss landscape bowl-shaped around the ground truth and improves iterative predictions on RNN, point cloud registration, and image alignment tasks.
-
An Overview of Algorithms for Contactless Cardiac Feature Extraction from Radar Signals: Advances and Challenges
The paper claims to be the first review of signal-processing algorithms for radar-based cardiac monitoring, with a new taxonomy and public dataset listings.
-
Real-Time Multimodal Signal Processing for HRI in RoboCup: Understanding a Human Referee
A NAO robot pipeline using MoveNet-based angle features and a CKCNN whistle detector recognizes referee signals in real time, with strong test numbers but 50% real-match gesture recall.
Discussion (0). Continue with ORCID to comment.