On Expected Accuracy

2019-05-01 · Ozan İrsoy

We empirically investigate the (negative) expected accuracy as an alternative loss function to cross entropy (negative log likelihood) for classification tasks. Coupled with softmax activation, it has small derivatives over most of its domain, and is therefore hard to optimize. A modified, leaky version is evaluated on a variety of classification tasks, including digit recognition, image classification, sequence tagging and tree tagging, using a variety of neural architectures such as logistic regression, multilayer perceptron, CNN, LSTM and Tree-LSTM. We show that it yields comparable or better accuracy compared to cross entropy. Furthermore, the proposed objective is shown to be more robust to label noise.

📄 PDF Abstract BibTeX arXiv:1905.00448

Code (0)

등록된 구현이 없습니다.

Tasks

Classification General Classification image-classification Image Classification regression

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Estimating Multi-label Accuracy using Labelset Distributions

2022-09-09 · Laurence A. F. Park, Jesse Read

A multi-label classifier estimates the binary label state (relevant vs irrelevant) for each of a set of concept labels, for any given instance. Probabilistic multi-label classifiers provide a predictive posterior distrib…

Decision Making

Latent Unexpected Recommendations

2020-07-27 · Pan Li, Alexander Tuzhilin

Unexpected recommender system constitutes an important tool to tackle the problem of filter bubbles and user boredom, which aims at providing unexpected and satisfying recommendations to target users at the same time. Pr…

Recommendation Systems

Random Search Hyper-Parameter Tuning: Expected Improvement Estimation and the Corresponding Lower Bound

2022-08-17 · Dan Navon, Alex M. Bronstein

Hyperparameter tuning is a common technique for improving the performance of neural networks. Most techniques for hyperparameter search involve an iterated process where the model is retrained at every iteration. However…

Adaptive kNN using Expected Accuracy for Classification of Geo-Spatial Data

2017-12-14 · Mark Kibanov, Martin Becker, Juergen Mueller, Martin Atzmueller 외

The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optim…

Classification General Classification

Latent Unexpected and Useful Recommendation

2019-05-04 · Pan Li, Alexander Tuzhilin

Providing unexpected recommendations is an important task for recommender systems. To do this, we need to start from the expectations of users and deviate from these expectations when recommending items. Previously propo…