Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy
3. května 2021
Řečníci
Akinori Ebihara
Řečník · 0 sledujících
Taiki Miyagawa
Řečník · 0 sledujících
Kazuyuki Sakurai
Řečník · 0 sledujících
Hitoshi Imaoka
Řečník · 0 sledujících
O prezentaci
Classifying sequential data as early and as accurately as possible is a challenging yet critical problem, especially when a sampling cost is high. One algorithm that achieves this goal is the sequential probability ratio test (SPRT), which is known as Bayes-optimal: it can keep the expected number of data samples as small as possible, given the desired error upper-bound. However, the original SPRT makes two critical assumptions that limit its application in real-world scenarios: (i) samples are independently and identically distributed, and (ii) the likelihood of the data being derived from each class can be calculated precisely. Here, we propose the SPRT-TANDEM, a deep neural network-based SPRT algorithm that overcomes the above two obstacles. The SPRT-TANDEM sequentially estimates the log-likelihood ratio of two alternative hypotheses by leveraging a novel Loss function for Log-Likelihood Ratio estimation (LLLR) while allowing correlations up to $N (\in \mathbb{N})$ preceding samples. In tests on one original and two public video databases, Nosaic MNIST, UCF101, and SiW, the SPRT-TANDEM achieves statistically significantly better classification accuracy than other baseline classifiers, with a smaller number of data samples. The code and Nosaic MNIST are publicly available at https://github.com/TaikiMiyagawa/SPRT-TANDEM.Classifying sequential data as early and as accurately as possible is a challenging yet critical problem, especially when a sampling cost is high. One algorithm that achieves this goal is the sequential probability ratio test (SPRT), which is known as Bayes-optimal: it can keep the expected number of data samples as small as possible, given the desired error upper-bound. However, the original SPRT makes two critical assumptions that limit its application in real-world scenarios: (i) samples are…
O organizátorovi (ICLR 2021)
The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
Zhlédnout později
Hayeon Lee, …
COVID-NET: Open Source Deep Learning Initiative for COVID-19 Clinical Decision Support
Zhlédnout později
Domain Generalization with MixStyle
Zhlédnout později
Kaiyang Zhou, …
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
Zhlédnout později
Probabilistic Numeric Convolutional Neural Networks
Zhlédnout později
Marc Finzi, …
