Idx_Testolin

Note: This material is presented to ensure timely dissemination of scholarly and technical work. By downloading any of these files, I'm requesting a copy of the publication to its author and I accept the terms of use.

Publications, Alberto Testolin

Learning Numerosity Representations with Transformers: Number Generation Tasks and Out-of-Distribution Generalization

Boccato, T., Testolin, A., & Zorzi, M. (2021). Learning Numerosity Representations with Transformers: Number Generation Tasks and Out-of-Distribution Generalization. Entropy, 23(7), 857.

PDF document icon Boccato et al. Entropy 2021.pdf — PDF document, 1.59 MB (1666161 bytes)

Learning orthographic structure with generative neural networks

Testolin, A., Stoianov, I., Sperduti, A., and Zorzi, M. (2016). Learning orthographic structure with generative neural networks. Cognitive Science.

PDF document icon Testolin_et_al-2015-Cognitive_Science.pdf — PDF document, 638 KB (653712 bytes)

Learning representation hierarchies by sharing visual features: a computational investigation of Persian character recognition with unsupervised deep learning

Sadeghi, Z., and Testolin, A. (2017). Learning representation hierarchies by sharing visual features: a computational investigation of Persian character recognition with unsupervised deep learning. Cognitive Processing.

PDF document icon Sadeghi&Testolin-2017-CogProc.pdf — PDF document, 1.02 MB (1066889 bytes)

Letter perception emerges from unsupervised deep learning and recycling of natural image features

Testolin, A., Stoianov, I., & Zorzi, M. (2017). Letter perception emerges from unsupervised deep learning and recycling of natural image features. Nature Human Behaviour, 1(9), 657.

PDF document icon Testolin, Stoianov, Zorzi - 2017 - NHB.pdf — PDF document, 4.51 MB (4733884 bytes)

Methodological Issues in Evaluating Machine Learning Models for EEG Seizure Prediction: Good Cross-Validation Accuracy Does Not Guarantee Generalization to New Patients

Shafiezadeh, S., Duma, G. M., Mento, G., Danieli, A., Antoniazzi, L., Del Popolo Cristaldi, F., ... & Testolin, A. (2023). Methodological issues in evaluating machine learning models for EEG seizure prediction: Good cross-validation accuracy does not guarantee generalization to new patients. Applied Sciences, 13(7), 4262.

PDF document icon Shafiezadeh et al. - Applied Sciences - 2023.pdf — PDF document, 2.36 MB (2477732 bytes)

Modeling language and cognition with deep unsupervised learning: a tutorial overview.

Zorzi, M., Testolin, A., & Stoianov, I. (2013). Modeling language and cognition with deep unsupervised learning: a tutorial overview. Frontiers in Psychology, 4 (515)

PDF document icon fpsyg-04-00515.pdf — PDF document, 2.62 MB (2745262 bytes)

Neural Networks for Sequential Data: a Pre‐training Approach based on Hidden Markov Models

Pasa, Luca, Alberto Testolin, and Alessandro Sperduti. "Neural Networks for Sequential Data: a Pre-training Approach based on Hidden Markov Models." Neurocomputing (2015).

PDF document icon 1-s2.0-S0925231215003689-main.pdf — PDF document, 888 KB (910322 bytes)

Numerosity discrimination in deep neural networks: Initial competence, developmental refinement and experience statistics

Testolin, A., Zou, W. Y., & McClelland, J. L. (2020). Numerosity discrimination in deep neural networks: Initial competence, developmental refinement and experience statistics. Developmental Science

PDF document icon Testolin.et.al.-DevSci-2020.pdf — PDF document, 1.40 MB (1468640 bytes)

Numerosity Representation in InfoGAN: An Empirical Study

Zanetti, A., Testolin, A., Zorzi, M., & Wawrzynski, P. (2019). Numerosity Representation in InfoGAN: An Empirical Study. In International Work-Conference on Artificial Neural Networks

PDF document icon Zanetti.et.al.2019-IWANN.pdf — PDF document, 2.37 MB (2485610 bytes)

On the Relationship between the Underwater Acoustic and Optical Channels

Diamant, R., Campagnaro, F., De Grazia, M. D. F., Casari, P., Testolin, A., Calzado, V. S., & Zorzi, M. (2017). On the Relationship between the Underwater Acoustic and Optical Channels. IEEE Transactions on Wireless Communications.

PDF document icon Diamant et al 2017 - IEEE TWCOM.pdf — PDF document, 1.79 MB (1875139 bytes)

Poor numerical performance of guppies tested in a Skinner box

Gatto, E., Testolin, A., Bisazza, A., Zorzi, M., & Lucon-Xiccato, T. (2020). Poor numerical performance of guppies tested in a Skinner box. Scientific Reports, 10(1), 1-9.

PDF document icon Gatto_et_al-2020-Scientific_Reports.pdf — PDF document, 1.25 MB (1311924 bytes)

Probabilistic Models and Generative Neural Networks: Towards an Unified Framework for Modeling Normal and Impaired Neurocognitive Functions

PDF document icon Testolin and Zorzi (2016) Perspective.pdf — PDF document, 1.04 MB (1087183 bytes)

QoE Multi-Stage Machine Learning for Dynamic Video Streaming

De Grazia, M. D. F., Zucchetto, D., Testolin, A., Zanella, A., Zorzi, M., & Zorzi, M. (2018). QoE Multi-Stage Machine Learning for Dynamic Video Streaming. IEEE Transactions on Cognitive Communications and Networking, 4(1), 146-161.

PDF document icon 2018-IEEETransCognCommNet.pdf — PDF document, 1.50 MB (1567947 bytes)

The Challenge of Modeling the Acquisition of Mathematical Concepts

Testolin, A. (2020). The challenge of modeling the acquisition of mathematical concepts. Frontiers in Human Neuroscience, 14.

PDF document icon Testolin - FrontHumNeurosc 2020.pdf — PDF document, 2.11 MB (2215396 bytes)

The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding

Testolin A, De Filippo De Grazia M and Zorzi M (2017) The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding. Front. Comput. Neurosci. 11:13.

PDF document icon fncom-11-00013.pdf — PDF document, 3.97 MB (4161613 bytes)

Visual sense of number vs. sense of magnitude in humans and machines

Testolin, A., Dolfi, S., Rochus, M., & Zorzi, M. (2020). Visual sense of number vs. sense of magnitude in humans and machines. Scientific reports, 10(1), 1-13.

PDF document icon Testolin_et_al-2020-Scientific_Reports.pdf — PDF document, 3.70 MB (3876567 bytes)