The paper evaluates three backpropagation‑free learning rules—Direct Feedback Alignment, Direct Random Target Projection, and NoProp—on 112 univariate time‑series classification datasets using 1D convolutional networks. Each method achieves mean F1 scores between 0.76 and 0.79, slightly below state‑of‑the‑art backpropagation baselines. The study also analyzes how dataset properties, especially intra‑class temporal variability, affect performance gaps and examines computational trade‑offs such as FLOPs, training speed, and memory usage.
arXiv:2607. 06796v1 Announce Type: cross Abstract: Deep learning has achieved remarkable success in various domains including time series analysis, computer vision and natural language processing.
The paper introduces the Recursive Time-Series Model (RTSM), a deep-learning architecture that uses a learned convolutional temporal tokenizer, a single-state weight‑tied refinement module, and a pooled classification readout to classify multivariate time‑series data. On the 30 UEA datasets, RTSM achieves a mean accuracy of 72.81% under validation‑based configuration, surpassing all 17 evaluated deep‑learning models and outperforming MambaSL by 1.60 percentage points. Ablation studies show that the proposed tokenizer and single‑state design outperform simpler convolutional embeddings and two‑state variants, and the full classifier reaches 86.10% mean accuracy compared to 84.79% for a tokenizer‑only classifier.
arXiv:2606. 06418v1 Announce Type: new Abstract: Many modern applications of deep learning involve training a neural network via a one-step prediction loss (e.
arXiv:2602. 13298v4 Announce Type: replace-cross Abstract: This paper presents a controlled comparative study of convolutional neural network (CNN) topology and image classification performance across the architectural families VGG, ResNet, and GoogLeNet, evaluated on CIFAR-10 under a unified training protocol.
arXiv:2605.06240v2 Announce Type: replace-cross Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inheri...
arXiv:2602. 20114v2 Announce Type: replace-cross Abstract: Machine unlearning (MU) refers to the post-training capability to remove (the influence of) training examples that are incorrect, biased, or leak sensitive/private information.
arXiv:2610.06942v1 Announce Type: new Abstract: Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time serie...
arXiv:2607. 07500v1 Announce Type: cross Abstract: Time series classification (TSC) is dominated by a two-stage paradigm: train a feature encoder -- either from scratch on the target dataset or via pretraining on large corpora -- and then fit a task-specific classifier on top.
arXiv:2607.01630v2 Announce Type: replace Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our...
arXiv:2603.14254v2 Announce Type: replace Abstract: Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods...
arXiv:2610.28602v1 Announce Type: cross Abstract: TS2Vec is one of the strongest self-supervised methods for time series classification, introduced in 2022. It is designed to be trained anew on every...
arXiv:2603. 15106v2 Announce Type: replace Abstract: Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requires DNN architectures to be specialized for each device separately.