Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Learning long-term dependencies with gradient descent is difficult
19945.5k citationsYoshua Bengio, P. Simard et al.IEEE Transactions on Neural Networksprofile →
Short-Term Traffic Flow Forecasting: An Experimental Comparison of Time-Series Analysis and Supervised Learning
Countries citing papers authored by Paolo Frasconi
Since
Specialization
Citations
This map shows the geographic impact of Paolo Frasconi's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Paolo Frasconi with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Paolo Frasconi more than expected).
This network shows the impact of papers produced by Paolo Frasconi. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Paolo Frasconi. The network helps show where Paolo Frasconi may publish in the future.
Co-authorship network of co-authors of Paolo Frasconi
This figure shows the co-authorship network connecting the top 25 collaborators of Paolo Frasconi.
A scholar is included among the top collaborators of Paolo Frasconi based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Paolo Frasconi. Paolo Frasconi is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Morante, Roser, et al.. (2012). A Statistical Relational Learning Approach to Identifying Evidence Based Medicine Categories. Florence Research (University of Florence). 579–589.20 indexed citations
6.
Kordjamshidi, Parisa, Paolo Frasconi, Martijn van Otterlo, Marie‐Francine Moens, & Luc De Raedt. (2011). Spatial relation extraction using relational learning. Lirias (KU Leuven). 1–6.4 indexed citations
7.
Frasconi, Paolo & Andrea Passerini. (2008). Predicting the Geometry of Metal Binding Sites from Protein Sequence. Florence Research (University of Florence). 21. 465–472.10 indexed citations
Landwehr, Niels, Andrea Passerini, Luc De Raedt, & Paolo Frasconi. (2006). kFOIL: learning simple relational kernels. Lirias (KU Leuven). 389–394.46 indexed citations
10.
Passerini, Andrea, Massimiliano Pontil, & Paolo Frasconi. (2002). From margins to probabilities in multiclass learning problems. UCL Discovery (University College London). 400–404.13 indexed citations
11.
Costa, Fabrizio, Paolo Frasconi, Vincenzo Lombardo, Patrick Sturt, & G. Soda. (2002). Enhancing first-pass attachment prediction. European Conference on Artificial Intelligence. 508–512.2 indexed citations
12.
Pollastri, Gianluca, Pierre Baldi, Alessandro Vullo, & Paolo Frasconi. (2002). Prediction of Protein Topologies Using Generalized IOHMMs and RNNs. Neural Information Processing Systems. 1473–1480.
13.
Frasconi, Paolo. (2001). Special issue on connectionist models for learning in structured domains. IEEE Transactions on Knowledge and Data Engineering.1 indexed citations
14.
Gori, Marco, Paolo Frasconi, & Alessandro Sperduti. (2000). Learning efficiently with neural networks: a theoretical comparison between structured and flat representations. European Conference on Artificial Intelligence. 301–305.7 indexed citations
15.
Baldi, Pierre, Søren Brunak, Paolo Frasconi, & Gianluca Pollastri. (1999). Bidirectional Dynamics for Protein Secondary Structure Prediction.4 indexed citations
16.
Costa, Fabrizio, Paolo Frasconi, & G. Soda. (1999). A topological transformation for hidden recursive modelsarchitecture networks.. The European Symposium on Artificial Neural Networks. 51–56.2 indexed citations
17.
Frasconi, Paolo, Marco Gori, & Alessandro Sperduti. (1997). On the efficient classification of data structures by neural networks. Research Padua Archive (University of Padua). 1066–1071.7 indexed citations
18.
Bengio, Yoshua, P. Simard, & Paolo Frasconi. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks. 5(2). 157–166.5453 indexed citations breakdown →
19.
Bengio, Yoshua & Paolo Frasconi. (1994). Diffusion of Credit in Markovian Models. Neural Information Processing Systems. 7. 553–560.10 indexed citations
20.
Bengio, Yoshua & Paolo Frasconi. (1993). Credit Assignment through Time: Alternatives to Backpropagation. Neural Information Processing Systems. 6. 75–82.28 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.