Zobrazeno 1 - 10
of 2 847
pro vyhledávání: '"A. Musat"'
Autor:
Musat, Tiberiu
In this paper, I introduce the retrieval problem, a simple reasoning task that can be solved only by transformers with a minimum number of layers. The task has an adjustable difficulty that can further increase the required number of layers to any ar
Externí odkaz:
http://arxiv.org/abs/2411.12118
Autor:
Garcia-Echeverria, J., Musat, D., Mahsafar, A., Mojaver, K. R., Rolston, D., Cowan, G., Liboiron-Ladouceur, O.
This paper presents a microring resonator-based weight function for neuromorphic photonic applications achieving a record-high precision of 11.3 bits and accuracy of 9.3 bits for 2 Gbps input optical signals. The system employs an all-analog self-ref
Externí odkaz:
http://arxiv.org/abs/2409.06604
Autor:
Musat, Tiberiu
Recent studies have revealed that neural networks learn interpretable algorithms for many simple problems. However, little is known about how these algorithms emerge during training. In this article, I study the training dynamics of a small neural ne
Externí odkaz:
http://arxiv.org/abs/2408.09414
Autor:
Gadd, Matthew, De Martini, Daniele, Bartlett, Oliver, Murcutt, Paul, Towlson, Matt, Widojo, Matthew, Muşat, Valentina, Robinson, Luke, Panagiotaki, Efimia, Pramatarov, Georgi, Kühn, Marc Alexander, Marchegiani, Letizia, Newman, Paul, Kunze, Lars
There is a growing academic interest as well as commercial exploitation of millimetre-wave scanning radar for autonomous vehicle localisation and scene understanding. Although several datasets to support this research area have been released, they ar
Externí odkaz:
http://arxiv.org/abs/2403.02845
Autor:
Fadeeva, Anastasiia, Schlattner, Philippe, Maksai, Andrii, Collier, Mark, Kokiopoulou, Efi, Berent, Jesse, Musat, Claudiu
The adoption of tablets with touchscreens and styluses is increasing, and a key feature is converting handwriting to text, enabling search, indexing, and AI assistance. Meanwhile, vision-language models (VLMs) are now the go-to solution for image und
Externí odkaz:
http://arxiv.org/abs/2402.15307
Autor:
Mitrevski, Blagoj, Rak, Arina, Schnitzler, Julian, Li, Chengkun, Maksai, Andrii, Berent, Jesse, Musat, Claudiu
Digital note-taking is gaining popularity, offering a durable, editable, and easily indexable way of storing notes in a vectorized form, known as digital ink. However, a substantial gap remains between this way of note-taking and traditional pen-and-
Externí odkaz:
http://arxiv.org/abs/2402.05804
Autor:
Musat, Bogdan, Andonie, Razvan
In recent years, pruning has emerged as a popular technique to reduce the computational complexity and memory footprint of Convolutional Neural Network (CNN) models. Mutual Information (MI) has been widely used as a criterion for identifying unimport
Externí odkaz:
http://arxiv.org/abs/2312.04926
Autor:
Musat, Bogdan, Andonie, Razvan
Structural pruning has become an integral part of neural network optimization, used to achieve architectural configurations which can be deployed and run more efficiently on embedded devices. Previous results showed that pruning is possible with mini
Externí odkaz:
http://arxiv.org/abs/2312.04918
Publikováno v:
International Conference on Document Analysis and Recognition - ICDAR 2023, pp. 98-114. Cham: Springer Nature Switzerland
On-line handwritten character segmentation is often associated with handwriting recognition and even though recognition models include mechanisms to locate relevant positions during the recognition process, it is typically insufficient to produce a p
Externí odkaz:
http://arxiv.org/abs/2309.03072
Digital ink (online handwriting) generation has a number of potential applications for creating user-visible content, such as handwriting autocompletion, spelling correction, and beautification. Writing is personal and usually the processing is done
Externí odkaz:
http://arxiv.org/abs/2306.03103