Related papers: Understanding training in superconducting accelera…
An automatic encoder (AE) extreme learning machine (ELM)-AE-ELM model is proposed to predict the NOx emission concentration based on the combination of mutual information algorithm (MI), AE, and ELM. First, the importance of practical…
This paper proposes an autoencoder (AE) that is used for improving the performance of once-class classifiers for the purpose of detecting anomalies. Traditional one-class classifiers (OCCs) perform poorly under certain conditions such as…
As a mental disorder progresses, it may affect brain structure, but brain function expressed in brain dynamics is affected much earlier. Capturing the moment when brain dynamics express the disorder is crucial for early diagnosis. The…
Theory and recent experiments concerning exchange-driven magnetic excitation (EDME) are reviewed. This phenomenon employs the exchange field produced by a narrowly distributed spin-polarized electron current to excite Larmor precession in a…
This paper presents our work of training acoustic event detection (AED) models using unlabeled dataset. Recent acoustic event detectors are based on large-scale neural networks, which are typically trained with huge amounts of labeled data.…
Accurate and robust prediction of patient's response to drug treatments is critical for developing precision medicine. However, it is often difficult to obtain a sufficient amount of coherent drug response data from patients directly for…
Unsupervised disentangled representation learning from the unlabelled audio data, and high fidelity audio generation have become two linchpins in the machine learning research fields. However, the representation learned from an unsupervised…
Like many other domains in Artificial Intelligence (AI), there are specific tasks in the field of AI in Education (AIEd) for which labels are scarce and expensive, such as predicting exam score or review correctness. A common way of…
Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high…
Masked autoencoders (MAEs) have displayed significant potential in the classification and semantic segmentation of medical images in the last year. Due to the high similarity of human tissues, even slight changes in medical images may…
Learning transferable representations for electroencephalography (EEG) remains challenging because EEG signals are inherently multi-channel and non-stationary. Channels observed at the same time provide coupled measurements of neural…
The Temporal Sampling Framework (TSF) theorizes that the characteristic phonological difficulties of dyslexia are caused by an atypical oscillatory sampling at one or more temporal rates. The LEEDUCA study conducted a series of…
Unsupervised learning is becoming more and more important recently. As one of its key components, the autoencoder (AE) aims to learn a latent feature representation of data which is more robust and discriminative. However, most AE based…
Exploiting the rapid advances in probabilistic inference, in particular variational Bayes and variational autoencoders (VAEs), for anomaly detection (AD) tasks remains an open research question. Previous works argued that training VAE…
Adversarial machine learning is a well-studied field of research where an adversary causes predictable errors in a machine learning algorithm through precise manipulation of the input. Numerous techniques have been proposed to harden…
Following the recent interest in applying the Hyperdimensional Computing paradigm in medical context to power up the performance of general machine learning applied to biomedical data, this study represents the first attempt at employing…
Teaching electromagnetism by demonstrating a practical application associated with learning content is an important teaching technique. Demonstrations are often performed through video-assisted procedures, and are usually limited to a…
Strong gravitational lensing can reveal the influence of dark-matter substructure in galaxies, but analyzing these effects from noisy, low-resolution images poses a significant challenge. In this work, we propose a masked autoencoder (MAE)…
Acoustic emotion recognition aims to categorize the affective state of the speaker and is still a difficult task for machine learning models. The difficulties come from the scarcity of training data, general subjectivity in emotion…
This work focuses on the training dynamics of one associative memory module storing outer products of token embeddings. We reduce this problem to the study of a system of particles, which interact according to properties of the data…