Giambattista Parascandolo

Publications21
h-index14
Citations1,717
Highly Influential Citations170
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • T. Virtanen
  • 315 Publications • 12,183 Citations
  • Yoshua Bengio
  • 848 Publications • 361,613 Citations
  • B. Schölkopf
  • 1,047 Publications • 123,514 Citations
  • David Silver
  • 121 Publications • 85,095 Citations
  • Publications
  • Influence
Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
TLDR
This work combines these two approaches in a convolutional recurrent neural network (CRNN) and applies it on a polyphonic sound event detection task and observes a considerable improvement for four different datasets consisting of everyday sound events.
View on ACM
Avoiding Discrimination through Causal Reasoning
TLDR
This work crisply articulate why and when observational criteria fail, thus formalizing what was before a matter of opinion and put forward natural causal non-discrimination criteria and develop algorithms that satisfy them.
View PDF on arXiv
Recurrent neural networks for polyphonic sound event detection in real life recordings
In this paper we present an approach to polyphonic sound event detection in real life recordings based on bi-directional long short term memory (BLSTM) recurrent neural networks (RNNs). A single…
View on IEEE
Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features
TLDR
The proposed SED system is compared against the state of the art mono channel method on the development subset of TUT sound events detection 2016 database and the usage of spatial and harmonic features are shown to improve the performance of SED.
View PDF on arXiv
Learning explanations that are hard to vary
TLDR
It is shown that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and `patchwork' solutions that sew together different strategies, instead of identifying invariances.
View PDF on arXiv
DCASE 2016 Acoustic Scene Classification Using Convolutional Neural Networks
TLDR
This workshop paper presents the use of a convolutional neural network trained to classify short sequences of audio, represented by their log-mel spectrogram, and proposes a training method that can be used when the system validation performance saturates as the training proceeds.
View Paper
Learning Independent Causal Mechanisms
TLDR
This work develops an algorithm to recover a set of independent (inverse) mechanisms from a sets of transformed data points, based on aset of experts that compete for data generated by the mechanisms, driving specialization.
View PDF on arXiv
Convolutional recurrent neural networks for bird audio detection
TLDR
In the proposed method, convolutional layers extract high dimensional, local frequency shift invariant features, while recurrent layers capture longer term dependencies between the features extracted from short time frames.
View on IEEE
Taming the waves: sine as activation function in deep neural networks
TLDR
This paper formally characterize why deep neural networks can indeed often be difficult to train even in very simple scenarios, and describes how the presence of infinitely many and shallow local minima emerges from the architecture.
Neural Symbolic Regression that Scales
TLDR
This paper procedurally generate an unbounded set of equations, and simultaneously pre-train a Transformer to predict the symbolic equation from a corresponding set of input-output-pairs, and shows empirically that this approach can re-discover a set of well-known physical equations and that it improves over time with more data and compute.
View PDF on arXiv
...
...