Related papers: Reinterpreting CTC training as iterative fitting

Commit Classification(CC) is an important task in software maintenance since it helps software developers classify code changes into different types according to their nature and purpose. This allows them to better understand how their…

Commit Classification (CC) is an important task in software maintenance, which helps software developers classify code changes into different types according to their nature and purpose. It allows developers to understand better how their…

Iterative Learning Control (ILC) is useful in spacecraft application for repeated high precision scanning maneuvers. Repetitive Control (RC) produces effective active vibration isolation based on frequency response. This paper considers ILC…

Supervised Causal Learning (SCL) has shown promise in causal discovery by framing it as a supervised learning problem. However, it suffers from significant out-of-distribution generalization challenges. We reveal three limitations of…

In regression, conformal prediction is a general methodology to construct prediction intervals in a distribution-free manner. Although conformal prediction guarantees strong statistical property for predictive inference, its inherent…

Inferring tie strengths in social networks is an essential task in social network analysis. Common approaches classify the ties as wea} and strong ties based on the strong triadic closure (STC). The STC states that if for three nodes, $A$,…

The acoustic-to-word model based on the connectionist temporal classification (CTC) criterion was shown as a natural end-to-end (E2E) model directly targeting words as output units. However, the word-based CTC model suffers from the…

This paper addresses the trajectory-tracking problem for discrete-time linear time-invariant systems with bounded parametric uncertainty, subject to hard constraints on system states, control inputs, and input rates. Unlike existing…

In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that…

The problem of predicting the training time of machine learning (ML) models has become extremely relevant in the scientific community. Being able to predict a priori the training time of an ML model would enable the automatic selection of…

Conformal risk control (CRC) is a recently proposed technique that applies post-hoc to a conventional point predictor to provide calibration guarantees. Generalizing conformal prediction (CP), with CRC, calibration is ensured for a set…

Knowledge Tracing (KT) aims to model a student's learning state over time and predict their future performance. However, traditional KT methods often face challenges in explainability, scalability, and effective modeling of complex…

Modern language models can generate high-quality short texts. However, they often meander or are incoherent when generating longer texts. These issues arise from the next-token-only language modeling objective. Recent work in…

Utilizing non-concurrent control data (NCC) in the analysis of late-entering arms in platform trials has recently received considerable attention. While incorporating NCC can lead to increased power and lower sample sizes, it might…

Analyzing sequential data is crucial in many domains, particularly due to the abundance of data collected from the Internet of Things paradigm. Time series classification, the task of categorizing sequential data, has gained prominence,…

On the one hand, there has been considerable progress on neural network verification in recent years, which makes certifying neural networks a possibility. On the other hand, neural networks in practice are often re-trained over time to…

We present a new distribution-free conformal prediction algorithm for sequential data (e.g., time series), called the \textit{sequential predictive conformal inference} (\texttt{SPCI}). We specifically account for the nature that time…

In this paper, we propose a simple but effective method to decode the output of Connectionist Temporal Classifier (CTC) model using a bi-directional neural language model. The bidirectional language model uses the future as well as the past…

Continual learning (CL) learns a sequence of tasks incrementally with the goal of achieving two main objectives: overcoming catastrophic forgetting (CF) and encouraging knowledge transfer (KT) across tasks. However, most existing techniques…

Convolutional neural networks (CNNs) have been successfully used in a range of tasks. However, CNNs are often viewed as "black-box" and lack of interpretability. One main reason is due to the filter-class entanglement -- an intricate…