Related papers: Device Modeling Bias in ReRAM-based Neural Network…

Imaging data has become widely available to study biological systems at various scales, for example the motile behaviour of bacteria or the transport of mRNA, and it has the potential to transform our understanding of key transport…

The implementation of current deep learning training algorithms is power-hungry, owing to data transfer between memory and logic units. Oxide-based RRAMs are outstanding candidates to implement in-memory computing, which is less…

Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet.…

Accurate predictions of when a component will fail are crucial when planning maintenance, and by modeling the distribution of these failure times, survival models have shown to be particularly useful in this context. The presented…

Neuroimaging data, particularly from techniques like MRI or PET, offer rich but complex information about brain structure and activity. To manage this complexity, latent representation models - such as Autoencoders, Generative Adversarial…

We consider model selection in stochastic bandit and reinforcement learning problems. Given a set of base learning algorithms, an effective model selection strategy adapts to the best learning algorithm in an online fashion. We show that by…

This work investigates the use of machine learning applied to the beam tracking problem in 5G networks and beyond. The goal is to decrease the overhead associated to MIMO millimeter wave beamforming. In comparison to beam selection (also…

Predictive uncertainty-a model's self awareness regarding its accuracy on an input-is key for both building robust models via training interventions and for test-time applications such as selective classification. We propose a novel…

Artificial neural networks have advanced the frontiers of reversible steganography. The core strength of neural networks is the ability to render accurate predictions for a bewildering variety of data. Residual modulation is recognised as…

Emerging device-based Computing-in-memory (CiM) has been proved to be a promising candidate for high-energy efficiency deep neural network (DNN) computations. However, most emerging devices suffer uncertainty issues, resulting in a…

Training on the Edge enables neural networks to learn continuously from new data after deployment on memory-constrained edge devices. Previous work is mostly concerned with reducing the number of model parameters which is only beneficial…

Bootstrapping labels from radiology reports has become the scalable alternative to provide inexpensive ground truth for medical imaging. Because of the domain specific nature, state-of-the-art report labeling tools are predominantly…

In this paper the application of uncertainty modeling to convolutional neural networks is evaluated. A novel method for adjusting the network's predictions based on uncertainty information is introduced. This allows the network to be either…

This paper presents a machine learning-based approach to correct inference errors caused by stuck-at faults in fully analog ReRAM-based neuromorphic circuits. Using a Design-Technology Co-Optimization (DTCO) simulation framework, we model…

Crossbar memory arrays have been touted as the workhorse of in-memory computing (IMC)-based acceleration of Deep Neural Networks (DNNs), but the associated hardware non-idealities limit their efficacy. To address this, cross-layer design…

Template-matching methods for visual tracking have gained popularity recently due to their good performance and fast speed. However, they lack effective ways to adapt to changes in the target object's appearance, making their tracking…

The ability to reliably predict the future quality of a wireless channel, as seen by the media access control layer, is a key enabler to improve performance of future industrial networks that do not rely on wires. Knowing in advance how…

Cortical plasticity is one of the main features that enable our ability to learn and adapt in our environment. Indeed, the cerebral cortex self-organizes itself through structural and synaptic plasticity mechanisms that are very likely at…

The deep neural network (DNN) has been proven effective in various domains. However, they often struggle to perform well on certain minority groups during inference, despite showing strong performance on the majority of data groups. This is…

Bayesian Neural Networks (BNNs) can overcome the problem of overconfidence that plagues traditional frequentist deep neural networks, and are hence considered to be a key enabler for reliable AI systems. However, conventional hardware…