Summer School on Neural Networks

9 papers10 directions
The Summer School on Neural Networks was an academic venue active from 1997 to 2004, focusing on the development and application of neural computing techniques. It functioned as a site for researchers to present work on both the theoretical aspects of neural architectures and their practical implementation in various computational domains. The venue’s contributions are documented through a collection of papers that address fundamental challenges in machine learning and computational neuroscience during this period. Research presented at the venue spanned several specialized areas, including speech enhancement, sequence modeling, and the processing of complex data structures. Specific topics included mean field methods for cortical network dynamics, probabilistic models of neuronal spike trains, and the application of dynamic Bayesian networks. The venue also explored event-based segmentation for control problems and adaptive signal processing, reflecting a broad interest in how neural models could be applied to real-world data and biological simulations. Frequent contributors to this venue included researchers such as Alessandro Sperduti, Amir Hussain, John Hertz, and Pierre Baldi. Their work at the Summer School on Neural Networks helped bridge the gap between biological insights and algorithmic developments. By hosting discussions on these varied topics, the venue served the machine learning community during a period of transition, providing a platform for exploring the intersection of signal processing, data analysis, and cognitive modeling.

Papers by Year

2004 1
2003 1
1997 7

Top Research Directions

Research directions most represented by papers from this venue.

Conductance Based Synaptic Modeling in Neural Networks 1
Mean Field Theory for Macroscopic Neural Dynamics 1
Navigating the Inference Efficiency Accuracy Tradeoff 1
Dynamic Bayesian Networks for Temporal Dependency Modeling 1
The Biological Abstraction Gap in Neural Networks 1
Understanding and Tightening Variational Bounds 1
Joint Latent State and Parameter Estimation 1
Variational Inference as an Optimization Problem 1
Gibbs Sampling for Posterior Inference in Latent Variable Models 1
The Computational Intractability of Exact Probabilistic Inference 1

Top Authors

AuthorPapers
Alessandro Sperduti1
Alexander Lerchner1
Amir Hussain1
Hava T Siegelmann1
Marco Gori1
Patrick Gallinari1
Pierre Baldi1
Zoubin Ghahramani1

Impactful Papers

Papers from this venue that shaped research clusters.

Influential

Papers

TitleYear
Nonlinear Adaptive Speech Enhancement Inspired by Early Auditory Processing2004
Mean Field Methods for Cortical Network Dynamics2003
Learning Dynamic Bayesian Networks1997
Neural Dynamics with Stochasticity1997
Neural Networks for Processing Data Structures1997
Parsing the Stream of Time: The Value of Event-Based Segmentation in a Complex Real-World Control Problem1997
Predictive Models for Sequence Modelling, Application to Speech and Character Recognition1997
Probabilistic Models of Neuronal Spike Trains1997
The Loading Problem: Topics in Complexity1997