Publications

📒 Books

S. Scardapane, Alice's Adventures in a Differentiable Wonderland -- Volume I, A Tour of the Land, arXiv preprint 2404.17625, 2024.
Link

👐 Preprints and whitepapers

[P15] Baiocchi, A., Spinelli, I., Nicolosi, A., Scardapane, S., Adaptive Point Transformer, arXiv:2401.14845, 2024.
Link

[P14] Hajij, M., et al., TopoX: A Suite of Python Packages for Machine Learning on Topological Domains, arXiv:2402.02441, 2024.
Link Code

[P13] Montagna, M., Scardapane, S., & Telyatnikov, L., Topological Deep Learning with State-Space Models: A Mamba Approach for Simplicial Complexes, arXiv:2409.12033, 2024.
Link

[P12] Telyatnikov, L., Bernardez, G., Montagna, M., Vasylenko, P., Zamzmi, G., Hajij, M., Schaub, M., Miolane, N., Scardapane, S., Papamarkou, T., TopoBenchmarkX: A Framework for Benchmarking Topological Deep Learning, arXiv:2406.06642, 2024.
Link Code

[P11] Candelori, B., Bardella, G., Spinelli, I., Pani, P., Ferraina, S., and Scardapane, S., Spatio-temporal transformers for decoding neural movement control, bioRxiv preprint, 2024.
Link

[P10] Devoto, A., Zhao, Y., Scardapane, S., and Minervini, P., A Simple and Effective L2 Norm-Based Strategy for KV Cache Compression, arXiv:2406.11430, 2024.
Link

[P9] Gambella, M., Pomponi, J., Scardapane, S., Roveri, M., NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks, arXiv:2401.13330, 2024.
Link

[P8] Guerra, M., Scardapane, S., Bianchi, F.M., Interpreting Temporal Graph Neural Networks with Koopman Theory, arXiv preprint arXiv:2410.13469, 2024.
Link

[P7] Torda, T., Ciardiello, A., Gargiulo, S., Grillo, G., Scardapane, S., Voena, C., Giagu, S., Influence based explainability of brain tumors segmentation in multimodal Magnetic Resonance Imaging, arXiv:2405.12222, 2024.
Link

[P6] Verdini, F., Melucci, P., Perna, S., Cariaggi, F., Gaido, M., Papi, S., Mazurek, S., Kasztelnik, M., Bentivogli, L., Bratières, S., Merialdo, P., Scardapane, S., How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not, arXiv:2409.17044, 2024.
Link

[P5] Pomponi, J., Devoto, A., Scardapane, S., Cascaded Scaling Classifier: class incremental learning with probability scaling, arXiv:2402.01262, 2024.
Link

[P4] Devoto, A., Alvetreti, F., Pomponi, J., Di Lorenzo, P., Minervini, P., Scardapane, S., Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning, arXiv preprint arXiv:2408.08670, 2024.
Link

[P3] Devoto, A., Petruzzi, S., Pomponi, J., Di Lorenzo, P., Scardapane, S., Adaptive Semantic Token Selection for AI-native Goal-oriented Communications, arXiv preprint arXiv:2405.02330, 2024.
Link

[P2] Wójcik, B., Devoto, A., Pustelnik, K., Minervini, P., Scardapane, S., Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference, arXiv:2312.10193, 2023.
Link Code

[P1] Telyatnikov, L., Bucarelli, M.S., Bernardez, G., Zaghen, O., Scardapane, S., Lio, P., Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design, arXiv:2310.07684, 2023.
Link

📰 Journal publications

[J56] Scardapane, S., Baiocchi, A., Devoto, A., Marsocci, V., Minervini, P., Pomponi, J., Conditional computation in neural networks: principles and research trends, Intelligenza artificiale, In press, pp. 1-16, 2024.
Link arXiv

[J55] Spinelli, I., Scardapane, S., & Uncini, A., A Meta-Learning Approach for Training Explainable Graph Neural Networks , IEEE Transactions on Neural Networks and Learning Systems, 35(4), pp. 4647-4655, 2024.
Link DOI arXiv Code

[J54] Ercolino, S., Devoto, A., Monorchio, L., Santini, M., Mazzaro, S., & Scardapane, S., On the robustness of vision transformers for in-flight monocular depth estimation, Industrial Artificial Intelligence, 1, pp. 1-14, 2023.
Link DOI

[J53] Devoto, A., Spinelli, I., Murabito, F., Chiovoloni, F., Musmeci, R., & Scardapane, S., Re-identification of objects from aerial photos with hybrid siamese neural networks, IEEE Transactions on Industrial Informatics, 19(3), pp. 2997-3005, 2023.
Link DOI

[J52] Pomponi, J., Dantoni, D., Nicolosi, A., & Scardapane, S., Rearranging pixels is a powerful black-box attack for RGB and infrared deep learning models., IEEE Access, 11, pp. 11298-11306, 2023.
Link DOI Code

[J51] Guerra, M., Scardapane, S., Bianchi, F.M., Probabilistic load forecasting with Reservoir Computing, IEEE Access, 11, pp. 145989-146002, 2023.
Link DOI arXiv Code

[J50] Comminiello, D., Nezamdoust, A., Scardapane, S., Scarpiniti, M., Hussain, A., & Uncini, A., A New Class of Efficient Adaptive Filters for Online Nonlinear Modeling, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 53(3), pp. 1384-1396, 2023.
Link arXiv

[J49] Guizzo, E., Weyde, T., Scardapane, S., & Comminiello, D., Learning Speech Emotion Representations in the Quaternion Domain, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31, pp. 1200-1212, 2023.
Link DOI Code

[J48] Pomponi, J., Scardapane, S., & Uncini, A., Continual Learning with Invertible Generative Models, Neural Networks, in press, pp. 1-10, 2023.
Link DOI arXiv Code

[J47] Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., Hussain, A., Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence, Cognitive Computation, in press, pp. 1-30, 2023.
Link DOI

[J46] Marsocci, V., Coletta, V., Ravanelli, R., Scardapane, S., & Crespi, M., Inferring 3D change detection from bitemporal optical images, ISPRS Journal of Photogrammetry and Remote Sensing, 196, pp. 325-339, 2023.
Link arXiv Code

[J45] Verdone, A., Scardapane, S., Panella, M., Explainable Spatio-Temporal Graph Neural Networks for multi-site photovoltaic energy production, Applied Energy, 353, Part B, pp. 1-13, 2023.
Link DOI

[J44] Spinelli, I., Bianchini, R., & Scardapane, S., Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks, Neural Networks, in press, pp. 1-25, 2023.
Link DOI arXiv

[J43] Maglianella, L., Nicoletti, L., Giagu, S., Napoli, C., & Scardapane, S., Convergent Approaches to AI Explainability for HEP Muonic Particles Pattern Recognition, Computing and Software for Big Science, 428.0, pp. 1-18, 2023.
Link DOI Code

[J42] Marsocci, V., Scardapane, S., Continual Barlow Twins: continual self-supervised learning for remote sensing semantic segmentation, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, pp. 5049-5060, 2023.
Link DOI arXiv Code

[J41] Scardapane, S., Gallicchio, C., Micheli, A., & Soriano, M.C., Guest Editorial: Trends in Reservoir Computing, Cognitive Computation, 15, pp. 1407-1408, 2023.
Link DOI

[J40] Giarnieri, E., & Scardapane, S., Towards Artificial Intelligence Applications in Next Generation Cytopathology, Biomedicines, 11(8), pp. 2225, 2023.
Link DOI

[J39] Sai, S., Mittal, U., Chamola, V., Huang, K., Spinelli, I., Scardapane, S., Tan, Z., Hussain, A., Machine Un-learning: An Overview of Techniques, Applications, and Future Directions, Cognitive Computation, Early access, pp. 1-25, 2023.
Link DOI

[J38] Asci, F., Scardapane, S., Zampogna, A., D'Onofrio, V., Testa, L., Patera, M., Falletti, M., Marsili, L., & Suppa, A., Handwriting Declines with Human Ageing: A Machine Learning Study, Frontiers in Aging Neuroscience, in press, pp. 1-14, 2022.
Link DOI
Press release: Sapienza | Adnkronos | Repubblica | Sky TG24

[J37] Pomponi, J., Scardapane, S., & Uncini, A., Centroids Matching: an efficient Continual Learning approach operating in the embedding space, Transactions on Machine Learning Research, online, pp. 1-15, 2022.
Link arXiv Code

[J36] Spinelli, I., Scardapane, S., Hussain, A., & Uncini, A., FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning, IEEE Transactions on Artificial Intelligence, 3(3), pp. 344-354, 2022.
Link DOI arXiv Code

[J35] Pomponi, J., Scardapane, S., & Uncini, A., A Probabilistic Re-Intepretation of Confidence Scores in Multi-Exit Models, Entropy, 24(1), pp. 1-14, 2022.
Link DOI Code

[J34] Lastilla, L., Ammirati, S., Firmani, D., Komodakis, N., Merialdo, P., & Scardapane, S., Self-supervised learning for medieval handwriting identification: A case study from the Vatican Apostolic Library, Information Processing & Management, 59(3), pp. 102875, 2022.
Link DOI

[J33] Bianchi, F.M., Scardapane, S., Løkse, S., & Jenssen, R., Reservoir computing approaches for representation and classification of multivariate time series, IEEE Transactions on Neural Networks and Learning Systems, 32(5), pp. 2169-237X, 2021.
Link DOI arXiv Code

[J32] Marsocci, V., Scardapane, S., & Komodakis, N., MARE: Self-Supervised Multi-Attention REsu-Net for Semantic Segmentation in Remote Sensing, Remote Sensing, 13(16), pp. 1-17, 2021.
Link DOI Code

[J31] Lilli, L., Giarnieri, E., & Scardapane, S., A Calibrated Multiexit Neural Network for Detecting Urothelial Cancer Cells, Computational and Mathematical Methods in Medicine, 1-11, pp. 428-437, 2021.
Link DOI

[J30] Spinelli, I., Scardapane, S., & Uncini A., Adaptive Propagation Graph Convolutional Network, IEEE Transactions on Neural Networks and Learning Systems, 32(10), pp. 4755-4760, 2021.
Link DOI arXiv Code

[J29] Scardapane, S., Spinelli, I., & Di Lorenzo, P., Distributed Training of Graph Convolutional Networks, IEEE Transactions on Signal and Information Processing over Networks, 7, pp. 87-100, 2021.
Link DOI arXiv

[J28] Pomponi, J., Scardapane, S., & Uncini, A., Bayesian Neural Networks With Maximum Mean Discrepancy Regularization, Neurocomputing, 453, pp. 428-437, 2021.
Link DOI arXiv Code

[J27] Pomponi, J., Scardapane, S., & Uncini, A., Structured Ensembles: an Approach to Reduce the Memory Footprint of Ensemble Methods, Neural Networks, In Press, pp. 1-41, 2021.
Link DOI arXiv Code

[J26] Baccarelli, E., Scardapane, S., Scarpiniti, M., Momenzadeh, A., Uncini, A., Optimized Training and Scalable Implementation of Conditional Deep Neural Networks with Early Exits for Fog-supported IoT applications, Information Sciences, 521, pp. 107-143, 2020.
Link DOI

[J25] Spinelli, I., Scardapane, S., & Uncini, A., Missing Data Imputation with Adversarially-trained Graph Convolutional Networks, Neural Networks, 129, pp. 249-260, 2020.
Link DOI arXiv Code

[J24] Pomponi J., Scardapane S., Lomonaco V., & Uncini A., Efficient Continual Learning in Neural Networks with Embedding Regularization, Neurocomputing, 397, pp. 139-148, 2020.
Link DOI arXiv Code

[J23] Vecchi, R., Scardapane, S., Comminiello, D., & Uncini, A., Compressing deep quaternion neural networks with targeted regularization, CAAI Transactions on Intelligence Technology, 5(3), pp. 172-176, 2020.
Link DOI arXiv

[J22] Scardapane, S., Van Vaerenbergh, S., Hussain, A., & Uncini, A., Complex-valued Neural Networks with Non-parametric Activation Functions, IEEE Transactions on Emerging Topics in Computational Intelligence, 4(2), pp. 140-150, 2020.
Link DOI arXiv

[J21] Scardapane, S., Scarpiniti, M., Baccarelli, E., & Uncini, A., Why should we add early exits to neural networks?, Cognitive Computation, 12(5), pp. 954-966, 2020.
Link DOI arXiv

[J20] Totaro, S., Hussain, A., & Scardapane, S., A Non-parametric Softmax for Improving Neural Attention in Time-Series Forecasting, Neurocomputing, 381, pp. 177-185, 2020.
Link DOI

[J19] Scardapane, S., Van Vaerenbergh, S., & Uncini, A., Kafnets: kernel-based non-parametric activation functions for neural networks, Neural Networks, 110, pp. 4947-4956, 2019.
Link DOI arXiv Code

[J18] Scardapane, S., & Di Lorenzo, P., Stochastic Training of Neural Networks via Successive Convex Approximations, IEEE Transactions on Neural Networks and Learning Systems, 29(10), pp. 4947-4956, 2018.
Link DOI arXiv Code

[J17] Scardapane, S., Wang, D. & Uncini, A., Bayesian Random Vector Functional-Link Networks for Robust Data Modeling, IEEE Transactions on Cybernetics, 48(7), pp. 2049-2059, 2018.
Link DOI arXiv Code

[J16] Scardapane, S. & Wang, D., Randomness in neural networks: an overview, WIREs Data Mining and Knowledge Discovery, 7(2), pp. 1-18, 2017.
Link DOI

[J15] Scardapane, S., Comminiello, D., Hussain, A. & Uncini, A., Group Sparse Regularization for Deep Neural Networks, Neurocomputing, 241, pp. 81-89, 2017.
Link DOI arXiv Code

[J14] Fierimonte, R., Scardapane, S., Uncini, A. & Panella, M., Fully Decentralized Semi-supervised Learning via Privacy-preserving Matrix Completion, IEEE Transactions on Neural Networks and Learning Systems, 28(11), pp. 2699-2711, 2017.
Link DOI Code

[J13] Scardapane, S. & Di Lorenzo, P., A Framework for Parallel and Distributed Training of Neural Networks, Neural Networks, 91, pp. 42-54, 2017.
Link DOI arXiv Code

[J12] Scardapane, S., Butcher, J., Bianchi, F.M., & Malik, Z., Advances in Biologically Inspired Reservoir Computing [Guest Editorial], Cognitive Computation, 9(3), pp. 295-296, 2017.
Link DOI

[J11] Scardapane, S., Panella, M., Comminiello, D., Hussain, A. & Uncini, A., Distributed reservoir computing with sparse readouts, IEEE Computational Intelligence Magazine, 11(4), pp. 59-70, 2016.
Link DOI Code

[J10] Bianchi, F.M., Scardapane, S., Rizzi, A., Uncini, A., & Sadeghian, A., Granular Computing Techniques for Classification and Semantic Characterization of Structured Data, Cognitive Computation, 8(3), pp. 442-461, 2016.
Link DOI

[J9] Scardapane, S., Fierimonte, R, Di Lorenzo, P., Panella, M. & Uncini, A., Distributed semi-supervised support vector machines, Neural Networks, 80, pp. 43-52, 2016.
Link DOI Code

[J8] Scardapane, S., Wang, D., & Panella, M., A decentralized training algorithm for Echo State Networks in distributed big data applications, Neural Networks, 78, pp. 65-74, 2016.
Link DOI Code

[J7] Scardapane, S. & Uncini, A., Semi-supervised Echo State Networks for Audio Classification, Cognitive Computation, 9(1), pp. 125-135, 2016.
Link DOI

[J6] Scardapane, S., Comminiello, D., Scarpiniti, M., & Uncini, A., A Semi-supervised Random Vector Functional-Link Network based on the Transductive Framework, Information Sciences, 364-365, pp. 156–166, 2016.
Link DOI

[J5] Comminiello, D., Scarpiniti, M., Scardapane, S., Parisi, R. & Uncini, A., Improving nonlinear modeling capabilities of functional link adaptive filters, Neural Networks, 69, pp. 51-59, 2015.
Link DOI

[J4] Bianchi, F. M., Scardapane, S., Uncini, A., Rizzi, A., Sadeghian, A., Prediction of telephone calls load using Echo State Network with exogenous variables, Neural Networks, 71, pp. 204-213, 2015.
Link DOI

[J3] Scardapane, S., Comminiello, D., Scarpiniti, M. & Uncini, A., Online Sequential Extreme Learning Machine With Kernels, IEEE Transactions on Neural Networks and Learning Systems, 26(9), pp. 2214-2200, 2015.
Link DOI

[J2] Scardapane, S., Scarpiniti, M., Bucciarelli, M., Colone, F., Mansueto, M. V., & Parisi, R., Microphone Array Based Classification for Security Monitoring in Unstructured Environments, AEU-International Journal of Electronics and Communications, 69(11), pp. 1715-1723, 2015.
Link DOI

[J1] Scardapane, S., Wang, D., Panella, M. & Uncini, A., Distributed Learning for Random Vector Functional-Link Networks, Information Sciences, 301, pp. 217-284, 2015.
Link DOI

📅 Conference publications

[C52] Papamarkou, T., et al., Position: Topological Deep Learning is the New Frontier for Relational Learning, International Conference on Machine Learning, pp. 1-27, 2024 (ICML).
Link arXiv

[C51] Battiloro, C., Spinelli, I., Telyatnikov, L., Bronstein, M., Scardapane, S., Di Lorenzo, P., From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module, International Conference on Learning Representations, pp. 1-22, 2024 (ICLR).
Link arXiv

[C50] Strinati, E.C., et al., Goal-Oriented and Semantic Communication in 6G AI-Native Networks: The 6G-GOALS Approach, EuCNC & 6G Summit, pp. 1-6, 2024 (EUCNC).
Link arXiv

[C49] Szatkowski, F., Wójcik, B., Piórczyński, M., Scardapane, S., Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion, Advances in Neural Information Processing Systems, pp. 1-11, 2024 (NeurIPS).
Link arXiv

[C48] Szatkowski, F., Wójcik, B., Piórczyński, M., Scardapane, S., Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion, Efficient Systems for Foundation Models Workshop @ ICML, pp. 1-11, 2024 (ICML).
Link arXiv

[C47] Contu, R., Marsocci, V., Coletta, V., Ravanelli, R., Scardapane, S., Urban 3D Change Detection with Deep Learning: Custom Data Augmentation Techniques, EGU General Assembly 2024, pp. 1, 2024 (Copernicus Meetings). Extended abstract No. EGU24-9729.
Link

[C46] Potì, A., Marsocci, V., Nicolosi, A., Scardapane, S., Assessing the Adaptability of Self-Supervised Learning Methods for Small-Scale Hyperspectral Imaging, 2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 8991-8994, 2024 (IEEE).
Link

[C45] Guerra, M., Spinelli, I., Scardapane, S., & Bianchi F.M., Explainability in subgraphs-enhanced Graph Neural Networks, Proceedings of the Northern Lights Deep Learning Workshop 2023, pp. 1-7, 2023 (Septentrio Academic Publishing).
Link arXiv Code

[C44] Telyatnikov, L., & Scardapane, S., EGG-GAE: scalable graph neural networks for tabular data imputation, Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 1-16, 2023 (PMLR 206:2661-2676).
Link arXiv Code

[C43] Moieez, H., Marsocci, V., Scardapane, S., Continual Self-Supervised Learning in Earth Observation with Embedding Regularization, 2023 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 5029-5032, 2023 (IEEE).
Link

[C42] Spinelli, I., Guerra, M., Bianchi F.M., Scardapane, S., Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability, 2023 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 229-234, 2023 (ESANN).
Link arXiv

[C41] Marsocci, V., Coletta, V., Ravanelli, R., Scardapane, S., & Crespi, M., New trends in urban change detection: detecting 3D changes from bitemporal optical images, EGU General Assembly 2023, pp. 1, 2023 (Copernicus Meetings). Extended abstract No. EGU23-13357.
Link

[C40] Torda, T., Gargiulo, S., Grillo, G., Ciardiello, A., Voena, C., Giagu, S., and Scardapane, S., Tracin in Semantic Segmentation of Tumor Brains in MRI, an Extended Approach, Proceedings of the 2nd AIxIA Workshop on Artificial Intelligence For Healthcare (AI*CH), pp. 1-10, 2023 (CEUR Workshop Proceedings).
Link

[C39] Papillon, M., et al., ICML 2023 Topological Deep Learning Challenge : Design and Results, Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML), pp. 3-8, 2023 (PMLR 221).
Link arXiv

[C38] Marsocci, V., Gonthier, N., Garioud, A., Scardapane, S., Mallet, C., GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 2075-2085, 2023 (IEEE/CVF).
Link arXiv

[C37] Pomponi, J., Scardapane, S., & Uncini, A., Pixle: a fast and effective black-box attack based on rearranging pixels, 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1-7, 2022 (IEEE).
Link arXiv Code

[C36] Verdone, A., Scardapane, S., & Panella, M., Multi-site Forecasting of Energy Time Series with Spatio-Temporal Graph Neural Networks, 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2022 (IEEE).
Link

[C35] Spasiano, F., Gennaro, G., & Scardapane, S., Evaluating Adversarial Attacks and Defences in Infrared Deep Learning Monitoring Systems, 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1-6, 2022 (IEEE).
Link

[C34] Farkhondeh, A., Palmero, C., Scardapane, S., & Escalera, S., Towards Self-Supervised Gaze Estimation, 2022 British Machine Vision Conference (BMVC), pp. 1-13, 2022 (The British Machine Vision Association and Society for Pattern Recognition).
Link arXiv

[C33] Vincenzo, V., Pellegrini, L., Cossu, A., Carta, A., Graffieti, G., Hayes, T.L., De Lange, M., Masana, M., Pomponi, J., van de Ven, G., Mundt, M., She, Q., Cooper, K., Forest, J., Belouadah, E., Calderara, S., Parisi, G.I., Cuzzolin, F., Tolias, A., Scardapane, S., Antiga, L., Amhad, S., Popescu, A., Kanan, C., van de Weijer, J., Tuytelaars, T., Bacciu, D., & Maltoni, D., Avalanche: an End-to-End Library for Continual Learning, Continual Learning in Computer Vision Workshop, CVPR 2021, pp. 1-11, 2021 (CVPR).
Link arXiv Code

[C32] Falvo, A., Comminiello, D., Scardapane, S., Scarpiniti, M., & Uncini, A., A Wide Multimodal Dense U-Net for Fast Magnetic Resonance Imaging, Proceedings of the 20120 28th European Signal Processing Conference (EUSIPCO), pp. 1274-1278, 2020 (IEEE).
Link

[C31] Iurcev, M., Diviacco, P., Scardapane, S., & Muciaccia, F., Recognition of marine seismic data features using convolutional neural networks, EGU General Assembly 2020, pp. 1, 2020 (EGU).
Link DOI

[C30] Celsi, M. R., Scardapane, S., & Comminiello, D., Quaternion Neural Networks for 3D Sound Source Localization in Reverberant Environments, Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1-6, 2020 (IEEE).
Link

[C29] Pomponi, J., Scardapane, S., & Uncini, A., Pseudo-Rehearsal for Continual Learning with Normalizing Flows, 4th Lifelong Learning Workshop, Thirty-seventh International Conference on Machine Learning, pp. 1-5, 2020 (ICML).
Link

[C28] Gallicchio, C., Lukoševičius‬, M., & Scardapane, S., Frontiers in Reservoir Computing, Proceedings of the 2020 European Symposium on Artificial Neural Networks (ESANN), pp. 559-566, 2020 (ESANN).
Link

[C27] Scardapane, S., Comminiello, D., Scarpiniti, M., Baccarelli, E., & Uncini, A., Differentiable Branching In Deep Networks for Fast Inference, 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1-5, 2020 (IEEE).
Link

[C26] Di Lorenzo, P., & Scardapane, S., Distributed Stochastic Nonconvex Optimization and Learning based on Successive Convex Approximation, Proceedings of the 2019 Asilomar Conference on Signals, Systems, and Computers, pp. 1-5, 2020 (IEEE).
Link DOI arXiv

[C25] Scardapane, S., Van Vaerenbergh, S., Comminiello, D., & Uncini, A., Widely Linear Kernels for Complex-Valued Kernel Activation Functions, Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1-5, 2019 (IEEE).
Link arXiv

[C24] Comminiello, D., Lella, M., Scardapane, S., & Uncini, A., Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Events, 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1-5, 2019 (IEEE).
Link DOI arXiv

[C23] Falvo, A., Comminiello, D., Scardapane, S., Scarpiniti, M., & Uncini, A., A Multimodal Dense U-Net For Accelerating Multiple Sclerosis MRI, Proceedings of the 2019 IEEE Machine Learning for Signal Processing Workshop (MLSP), pp. 1-6, 2019 (IEEE).
Link DOI

[C22] Comminiello, D., Scarpiniti, M., Scardapane, S., Azpicueta-Ruiz, L. A., & Uncini, A., Combined Sparse Regularization for Nonlinear Adaptive Filters, Proceedings of the 2018 26th European Signal Processing Conference (EUSIPCO), pp. 336-340, 2018 (IEEE).
Link DOI

[C21] Bianchi, F. M., Scardapane, S., Løkse, S., & Jenssen, R., Bidirectional deep-readout echo state networks, Proceedings of the 2018 European Symposium on Artificial Neural Networks (ESANN), pp. 425-430, 2018 (ESANN).
Link arXiv Code

[C20] Scardapane, S., Van Vaerenbergh, S., Comminiello, D., & Uncini, A., Improving Graph Convolutional Networks with Non-Parametric Activation Functions, Proceedings of the 2018 26th European Signal Processing Conference (EUSIPCO), pp. 872-876, 2018 (IEEE).
Link DOI arXiv

[C19] Comminiello, D., Scarpiniti, M, Scardapane, S., & Uncini, A., Sparse Functional Link Adaptive Filter Using an ℓ1-Norm Regularization, Proceedings of the 2018 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5, 2018 (IEEE).
Link

[C18] Scardapane, S., Van Vaerenbergh, S., Comminiello, D., Totaro, S., & Uncini, A., Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions, Proceedings of the 2018 IEEE Machine Learning for Signal Processing Workshop (MLSP), pp. 1-6, 2018 (IEEE).
Link DOI arXiv

[C17] Scardapane, S., Stoffl, L., Röhrbein, F. & Uncini, A., On the Use of Deep Recurrent Neural Networks for Detecting Audio Spoofing Attacks, 2017 International Joint Conference on Neural Networks (IJCNN), pp. 3483-3490, 2017 (IEEE).
Link

[C16] Van Vaerenbergh, S., Scardapane, S., & Santamaria, I., Recursive Multikernel Filters Exploiting Nonlinear Temporal Structure, 2017 25th European Signal Processing Conference (EUSIPCO), pp. 2743-2747, 2017 (Eurasip).
Link DOI arXiv

[C15] Firmani, D., Merialdo, P., Nieddu, E., & Scardapane, S., In Codice Ratio: OCR of Handwritten Latin Documents using Deep Convolutional Networks, Proceedings of the 11th International Workshop on Artificial Intelligence for Cultural Heritage (AI*CH), pp. 9-16, 2017 (CEUR Workshop Proceedings).
Link

[C14] Di Lorenzo, P. & Scardapane, S., Parallel and Distributed Training of Neural Networks via Successive Convex Approximation, 2016 IEEE International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1-6, 2016 (IEEE).
Link DOI Code

[C13] Scardapane, S., Scarpiniti, M., Comminiello, D. & Uncini, A., Diffusion Spline Adaptive Filtering, 2016 24th European Signal Processing Conference (EUSIPCO), pp. 1498-1502, 2016 (Eurasip).
Link Code

[C12] Scardapane, S., Altilio, R., Panella, M. & Uncini, A., Distributed Spectral Clustering based on Euclidean Distance Matrix Completion, 2016 International Joint Conference on Neural Networks (IJCNN), pp. 3093-3100, 2016 (IEEE).
Link DOI

[C11] Scardapane, S., Panella, M., Comminiello, D., & Uncini, A., Learning from Distributed Data Sources Using Random Vector Functional-Link Networks, Procedia Computer Science, pp. 53, 468-477, 2015 (Elsevier).
Link DOI

[C10] Comminiello D., Scardapane, S., Scarpiniti, M., Parisi, R. & Uncini, A., Functional Link Expansions for Nonlinear Modeling of Audio and Speech Signals, 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2015 (IEEE).
Link DOI

[C9] Scardapane, S., Fierimonte, R., Wang, D., Panella, M. & Uncini, A., Distributed Music Classification Using Random Vector Functional-Link Nets, 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1-8, 2015 (IEEE).
Link

[C8] Bianchi, F. M., Scardapane, S., Livi, L., Uncini, A., & Rizzi, A., An interpretable graph-based image classifier, 2014 International Joint Conference on Neural Networks (IJCNN), pp. 2339-2346, 2014 (IEEE).
Link DOI

[C7] Scardapane, S., Comminiello, D., Scarpiniti, M., & Uncini, A., GP-based kernel evolution for L2-Regularization Networks, 2014 IEEE Congress on Evolutionary Computation (CEC), pp. 1674-1681, 2014 (IEEE).
Link

[C6] Scardapane, S., Nocco, G., Comminiello, D., Scarpiniti, M., & Uncini, A., An effective criterion for pruning reservoir’s connections in Echo State Networks, 2014 International Joint Conference on Neural Networks (IJCNN), pp. 1205-1212, 2014 (IEEE).
Link DOI

[C5] Comminiello, D., Scardapane, S., Scarpiniti, M., & Uncini, A., User-Driven Quality Enhancement for Audio Signal Processing, Audio Engineering Society Convention 134, pp. , 2013 (Audio Engineering Sociery).
Link Code

[C4] Scardapane, S., Comminiello, D., Scarpiniti, M., & Uncini, A., Music classification using extreme learning machines, 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA), pp. 377-381, 2013 (IEEE).
Link DOI

[C3] Comminiello, D., Scardapane, S., Scarpiniti, M., & Uncini, A., Interactive quality enhancement in acoustic echo cancellation, 2013 36th International Conference on Telecommunications and Signal Processing (TSP), pp. 488-492, 2013 (IEEE).
Link DOI Code

[C2] Alemanno, A., Travaglini, A., Scardapane, S., Comminiello, D., & Uncini, A., A Framework for Adaptive Real-Time Loudness Control, Audio Engineering Society Convention 134, pp. , 2013 (Audio Engineering Sociery).
Link

[C1] Comminiello, D., Scardapane, S., Scarpiniti, M., Parisi, R., & Uncini, A., Convex combination of MIMO filters for multichannel acoustic echo cancellation, 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA), pp. 778-782, 2013 (IEEE).
Link DOI

📚 Book publications

[B23] Carraro, A., Saurio, G., López-Maestresalas, A., Scardapane, S., Marinello, F., Convolutional Neural Networks for the Detection of Esca Disease Complex in Asymptomatic Grapevine Leaves, Image Analysis and Processing - ICIAP 2023 Workshops, pp. 1-10, 2023 (Lecture Notes in Computer Science, vol 14365. Springer, Cham).
Link DOI

[B22] Saurio, G., Muscas, M., Spinelli, I., Rughetti, V., Della Giovampaola, I., Scardapane, S., ArcheoWeedNet: Weed Classification in the Parco archeologico del Colosseo, Image Analysis and Processing - ICIAP 2023 Workshops, pp. 1-10, 2023 (Lecture Notes in Computer Science, vol 14365. Springer, Cham).
Link DOI

[B21] Copur, O., Nakip, M., Scardapane, S., & Slowack Jürgen, Engagement Detection with Multi-Task Training in E-Learning Environments, Image Analysis and Processing – ICIAP 2022, pp. 411-422, 2022 (Springer).
Link DOI arXiv Code

[B20] Scarpiniti, M., Scardapane, S., Comminiello, S., & Uncini A., Music Genre Classification Using Stacked Auto-Encoders, Neural Approaches to Dynamics of Signal Exchanges, pp. 11-19, 2020 (Springer).
Link DOI

[B19] Falvo A., Comminiello D., Scardapane S., Finesi G., Scarpiniti M., & Uncini A., A Multimodal Deep Network for the Reconstruction of T2W MR Images, Progresses in Artificial Intelligence and Neural Systems, pp. 423-431, 2020 (Springer).
Link DOI arXiv

[B18] Grassucci, E., Scardapane S., Comminiello, D., & Uncini A., Flexible Generative Adversarial Networks with Non-parametric Activation Functions, Progresses in Artificial Intelligence and Neural Systems, pp. 67-77, 2020 (Springer).
Link DOI arXiv

[B17] Spinelli, I., Scardapane, S., Scarpiniti, M., & Uncini, A., Efficient data augmentation using graph imputation neural networks, Progresses in Artificial Intelligence and Neural Systems, pp. 43-68, 2020 (Springer).
Link DOI arXiv

[B16] Gallicchio, C., & Scardapane, S., Deep randomized neural networks, Recent Trends in Learning From Data, pp. 43-68, 2020 (Springer).
Link DOI arXiv

[B15] Scarpiniti, M., Scardapane, S., Comminiello, D., Parisi, R. & Uncini, A., Separation of Drum and Bass from Monaural Tracks, Neural Advances in Processing Nonlinear Dynamic Signals, pp. 141-151, 2019 (Springer).
Link DOI

[B14] Scardapane, S., Nieddu, E., Firmani, D., & Merialdo, P., Multikernel activation functions: formulation and a case study, INNSBDDL 2019: Recent Advances in Big Data and Deep Learning, pp. 320-329, 2019 (Springer).
Link DOI arXiv

[B13] Comminiello, D., Scarpiniti, M., Scardapane, S., Parisi, R. & Uncini, A., A Low-Complexity Linear-in-the-Parameters Nonlinear Filter for Distorted Speech Signals, Neural Advances in Processing Nonlinear Dynamic Signals, pp. 107-117, 2019 (Springer).
Link DOI

[B12] Scardapane, S., Scarpiniti, M., Comminiello, D. & Uncini, A., Learning activation functions from data using cubic spline interpolation, Neural Advances in Processing Nonlinear Dynamic Signals, pp. 73-83, 2019 (Springer).
Link DOI arXiv Code

[B11] Scardapane, S., Chen, J., & Richard, C., Adaptation and learning over networks for nonlinear system modeling, Adaptive Learning Methods for Nonlinear System Modeling, pp. 223-242, 2018 (Elsevier).
Link DOI arXiv

[B10] Scardapane, S., Altilio, R., Ciccarelli, V., Uncini, A. & Panella, M., Privacy-Preserving Data Mining for Distributed Medical Scenarios, Multidisciplinary Approaches to Neural Computing, pp. 119-128, 2017 (Springer).
Link DOI

[B9] Scarpiniti, M., Scardapane, S., Comminiello, D., Parisi, R. & Uncini, A., Effective Blind Source Separation Based on the Adam Algorithm, Multidisciplinary Approaches to Neural Computing, pp. 57-66, 2017 (Springer).
Link DOI arXiv

[B8] Comminiello, D., Scarpiniti, M., Scardapane, S., Parisi, R., & Uncini, A., A Nonlinear Acoustic Echo Canceller with Improved Tracking Capabilities, Recent Advances in Nonlinear Speech Processing, pp. 235-243, 2016 (Springer).
Link DOI

[B7] Fierimonte, R., Scardapane, S., Panella, M., & Uncini, A., A Comparison of Consensus Strategies for Distributed Learning of Random Vector Functional-Link Networks, Advances in Neural Networks: Computational Intelligence and ICT, pp. 143-152, 2016 (Springer).
Link DOI

[B6] Scardapane, S., Danilo, C., Scarpiniti, M., Parisi, R. & Uncini, A., Benchmarking Functional Link Expansions for Audio Classification Tasks, Advances in Neural Networks: Computational Intelligence and ICT, pp. 133-141, 2016 (Springer).
Link DOI

[B5] Scardapane, S., Comminiello, D., Scarpiniti, M., & Uncini, A., Significance-Based Pruning for Reservoir’s Neurons in Echo State Networks, Advances in Neural Networks: Computational and Theoretical Issues, pp. 31-38, 2015 (Springer).
Link DOI

[B4] Comminiello, D., Scardapane, S., Scarpiniti, M., Parisi, R. & Uncini, A., Online Selection of Functional Links for Nonlinear System Identification, Advances in Neural Networks: Computational and Theoretical Issues, pp. 39-47, 2015 (Springer).
Link DOI

[B3] Scarpiniti, M., Comminiello, D., Scardapane, S., Parisi, R., & Uncini, A., Proportionate Algorithms for Blind Source Separation, Recent Advances of Neural Network Models and Applications, pp. 99-106, 2014 (Springer).
Link DOI

[B2] Scardapane, S., Comminiello, D., Scarpiniti, M., & Uncini, A., A Preliminary Study on Transductive Extreme Learning Machines, Recent Advances of Neural Network Models and Applications, pp. 25-32, 2014 (Springer).
Link DOI

[B1] Scardapane, S., Comminiello, D., Scarpiniti, M., Parisi, R., & Uncini, PM10 Forecasting Using Kernel Adaptive Filtering: An Italian Case Study, Neural Nets and Surroundings, pp. 93-100, 2013 (Springer).
Link DOI

TL;DR 👇

📒 Books

👐 Preprints and whitepapers

📰 Journal publications

📅 Conference publications

📚 Book publications