Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 5 of 5 for “"Confidence Estimation"”.
-
Neural Network Supervision: Notes on Loss Functions, Labels and Confidence Estimation
… consider the problem of quantifying prediction confidence in the regression setting. We propose two novel algorithms for emitting calibrated prediction intervals for neural network regressors, at any given confidence level. The two algorithms require binning of the output space and training the …
-
Confidence estimation of the ratio of variances of two log-normal populations
This study investigates asymptotic and bootstrap confidence intervals (CIs) for the ratio of variances of two independent log-normal distributions. Extensive simula-tions were conducted to evaluate the performance of these CIs under varying sample sizes (10 to 350) and variance ratios, with one …
-
Assessing classification confidence using a weighted exponential based technique with the Learn++ incremental learning algorithm
… to add the capability of assessing its own confidence. Estimation of the true generalization performance of the classifier as well as the confidences on classification of individual data instances is investigated separately. Several confidence estimation techniques are explored such as …
-
Attention-Based Encoder-Decoder Models for Speech Processing
… speech processing tasks - speech recognition, confidence estimation and speaker diarisation. Speech recognition technology is widely used in voice assistants and dictation systems. It converts speech signals into text. Traditionally, Hidden Markov Models (HMMs), as a generative …
-
Speech-Based Emotion Modelling and Mental Disorder Detection
… quantify the uncertainty in emotion distribution estimation by learning an utterance-specific prior distribution. Representing emotion as a distribution offers not only a more comprehensive representation of emotional content but also an inclusive representation of human opinions. The challenge of …