Search Results for author:
Found 6 papers, 1 papers with code
Probabilistic Transformers
We show that Transformers are Maximum Posterior Probability estimators for Mixtures of Gaussian Models.
Deep Active Object Recognition by Joint Label and Action Prediction
The results of experiments suggest that the proposed model equipped with Dirichlet state encoding is superior in performance, and selects images that lead to better training and higher accuracy of label prediction at test time.
Variable and Fixed Interval Exponential Smoothing
Exponential smoothers are a simple and memory efficient way to compute running averages of time series.
An Alternative to Low-level-Sychrony-Based Methods for Speech Detection
Here we show that with the proper visual features (in this case movements of various facial muscle groups), a very accurate detector of speech can be created that does not use the audio signal at all.
Facial Expression Recognition
Facial Expression Recognition (FER)
+4
Whose Vote Should Count More: Optimal Integration of Labels from Labelers of Unknown Expertise
However, using these services to label large databases brings with it new theoretical and practical challenges: (1) The labelers may have wide ranging levels of expertise which are unknown a priori, and in some cases may be adversarial; (2) images may vary in their level of difficulty; and (3) multiple labels for the same image must be combined to provide an estimate of the actual label of the image.
Optimization on a Budget: A Reinforcement Learning Approach
Reinforcement learning (RL) is a machine learning approach to learn optimal controllers by examples and thus is an obvious candidate to improve the heuristic-based controllers implicit in the most popular and heavily used optimization algorithms.
