Related papers: Bit-Identical Medical Deep Learning via Structured…
Structured prediction is the cornerstone of several machine learning applications. Unfortunately, in structured prediction settings with expressive inter-variable interactions, exact inference-based learning algorithms, e.g. Structural SVM,…
Multi-task learning can suffer from destructive task interference, where jointly trained models underperform single-task baselines and limit generalization. To improve generalization performance in breast ultrasound-based tumor segmentation…
It is well known that the initialization of weights in deep neural networks can have a dramatic impact on learning speed. For example, ensuring the mean squared singular value of a network's input-output Jacobian is $O(1)$ is essential for…
Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-distribution (OOD) examples or making a wrong prediction.…
To reduce random access memory (RAM) requirements and to increase speed of recognition algorithms we consider a weight discretization problem for trained neural networks. We show that an exponential discretization is preferable to a linear…
Deep brain stimulation (DBS) has the potential to improve the quality of life of people with a variety of neurological diseases. A key challenge in DBS is in the placement of a stimulation electrode in the anatomical location that maximizes…
With the rising prevalence of cardiovascular diseases, electrocardiograms (ECG) remain essential for the non-invasive detection of cardiac abnormalities. This study presents a comprehensive evaluation of deep neural network architectures…
Identifying epileptic seizures through analysis of the electroencephalography (EEG) signal becomes a standard method for the diagnosis of epilepsy. Manual seizure identification on EEG by trained neurologists is time-consuming,…
Electrocardiograms (ECGs) provide non-invasive measurements of heart activity and are established tools for detecting cardiac arrhythmias. Although supervised machine learning has emerged as a promising approach for automated heartbeat…
Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning. However, the laborious and expensive annotation process lags down the speed of further advances.…
Port-Hamiltonian neural networks have shown promising results in the identification of nonlinear dynamics of complex systems, as their combination of physical principles with data-driven learning allows for accurate modelling. However, due…
Optimization with matrix gradient orthogonalization has recently demonstrated impressive results in the training of deep neural networks (Jordan et al., 2024; Liu et al., 2025). In this paper, we provide a theoretical analysis of this…
Positive-Unlabeled (PU) learning aims to learn a model with rare positive samples and abundant unlabeled samples. Compared with classical binary classification, the task of PU learning is much more challenging due to the existence of many…
Deep learning methods for electronic-structure Hamiltonian prediction has offered significant computational efficiency advantages over traditional DFT methods, yet the diversity of atomic types, structural patterns, and the high-dimensional…
The search for an application of near-term quantum devices is widespread. Quantum Machine Learning is touted as a potential utilisation of such devices, particularly those which are out of the reach of the simulation capabilities of…
Existing neural active learning algorithms have aimed to optimize the predictive performance of neural networks (NNs) by selecting data for labelling. However, other than a good predictive performance, being robust against random parameter…
Most EEG-based Brain-Computer Interfaces (BCIs) require a considerable amount of training data to calibrate the classification model, owing to the high variability in the EEG data, which manifests itself between participants, but also…
The high computation, memory, and power budgets of inferring convolutional neural networks (CNNs) are major bottlenecks of model deployment to edge computing platforms, e.g., mobile devices and IoT. Moreover, training CNNs is time and…
Originated from distributed learning, federated learning enables privacy-preserved collaboration on a new abstracted level by sharing the model parameters only. While the current research mainly focuses on optimizing learning algorithms and…
Despite of the pain and limited accuracy of blood tests for early recognition of cardiovascular disease, they dominate risk screening and triage. On the other hand, heart rate variability is non-invasive and cheap, but not considered…