paper-with-me

홈 › Papers

Traversing Latent Space using Decision Ferns

2018-12-06 · Yan Zuo, Gil Avraham, Tom Drummond

The practice of transforming raw data to a feature space so that inference can be performed in that space has been popular for many years. Recently, rapid progress in deep neural networks has given both researchers and practitioners enhanced methods that increase the richness of feature representations, be it from images, text or speech. In this work we show how a constructed latent space can be explored in a controlled manner and argue that this complements well founded inference methods. For constructing the latent space a Variational Autoencoder is used. We present a novel controller module that allows for smooth traversal in the latent space and construct an end-to-end trainable framework. We explore the applicability of our method for performing spatial transformations as well as kinematics for predicting future latent vectors of a video sequence.

📄 PDF Abstract BibTeX arXiv:1812.02636

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

rFerns: An Implementation of the Random Ferns Method for General-Purpose Machine Learning

2012-02-06 · Miron B. Kursa

In this paper I present an extended implementation of the Random ferns algorithm contained in the R package rFerns. It differs from the original by the ability of consuming categorical and numerical attributes instead of…

AttributeBIG-bench Machine Learning

Counterfactual Explanations via Riemannian Latent Space Traversal

2024-11-04 · Paraskevas Pegios, Aasa Feragen, Andreas Abildtrup Hansen, Georgios Arvanitidis

The adoption of increasingly complex deep models has fueled an urgent need for insight into how these models make predictions. Counterfactual explanations form a powerful tool for providing actionable explanations to pra…

counterfactualCounterfactual ExplanationDecoder

A Comparison of Random Forests and Ferns on Recognition of Instruments in Jazz Recordings

2013-05-22 · Alicja A. Wieczorkowska, Miron B. Kursa

In this paper, we first apply random ferns for classification of real music recordings of a jazz band. No initial segmentation of audio data is assumed, i.e., no onset, offset, nor pitch data are needed. The notion of ra…

ClassificationGeneral Classification

Multi-label Ferns for Efficient Recognition of Musical Instruments in Recordings

2014-03-30 · Miron B. Kursa, Alicja A. Wieczorkowska

In this paper we introduce multi-label ferns, and apply this technique for automatic classification of musical instruments in audio recordings. We compare the performance of our proposed method to a set of binary random …

ClassificationGeneral Classification

Sparse Hierarchical Table Ensemble

2021-09-29 · Guy Farjon, Aharon Bar Hillel

Deep learning for tabular data is drawing increasing attention, with recent work attempting to boost the accuracy of neuron-based networks. However, when computational capacity is low as in Internet of Things (IoT), dron…

Deep Learning