A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level

Posted by klaurent MIT

Kavli Affiliate: Avi Shporer | First 5 Authors: Iddo Drori, Sarah Zhang, Reece Shuttleworth, Leonard Tang, Albert Lu | Summary: We demonstrate that a neural network pre-trained on text and fine-tuned on code solves mathematics course problems, explains solutions, and generates new questions at a human level. We automatically synthesize programs using few-shot learning and […]


Continue.. A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level

QEMind: Alibaba’s Submission to the WMT21 Quality Estimation Shared Task

Posted by klaurent Peking

Kavli Affiliate: Ke Wang | First 5 Authors: Jiayi Wang, Ke Wang, Boxing Chen, Yu Zhao, Weihua Luo | Summary: Quality Estimation, as a crucial step of quality control for machine translation, has been explored for years. The goal is to investigate automatic methods for estimating the quality of machine translation results without reference translations. […]


Continue.. QEMind: Alibaba’s Submission to the WMT21 Quality Estimation Shared Task

DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classification

Posted by klaurent Chicago

Kavli Affiliate: Brian Nord | First 5 Authors: Aleksandra Ćiprijanović, Diana Kafkes, Gregory Snyder, F. Javier Sánchez, Gabriel Nathan Perdue | Summary: Data processing and analysis pipelines in cosmological survey experiments introduce data perturbations that can significantly degrade the performance of deep learning-based models. Given the increased adoption of supervised deep learning methods for processing […]


Continue.. DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classification

Deployed MDI-QKD and Bell-State Measurements Coexisting with Standard Internet Data and Networking Equipment

Posted by klaurent Delft

Kavli Affiliate: Wolfgang Tittel | First 5 Authors: Remon C. Berrevoets, Thomas Middelburg, Raymond F. L. Vermeulen, Luca Della Chiesa, Federico Broggi | Summary: The forthcoming quantum Internet is poised to allow new applications not possible with the conventional Internet. The ability for both quantum and conventional networking equipment to coexist on the same fiber […]


Continue.. Deployed MDI-QKD and Bell-State Measurements Coexisting with Standard Internet Data and Networking Equipment

Neutrino Observations of LHAASO Sources: Present and Prospect

Posted by klaurent Peking

Kavli Affiliate: Zhuo Li | First 5 Authors: Tian-Qi Huang, Zhuo Li, , , | Summary: The Large High Altitude Air Shower Observatory (LHAASO) observed a dozen of gamma-ray sources with significant emission above 100 TeV, which are the possible accelerators of PeV cosmic-rays. The neutrino observations are required to answer whether these high energy […]


Continue.. Neutrino Observations of LHAASO Sources: Present and Prospect

Neutrino Observations of LHAASO Sources: Present Constraints and Future Prospects

Posted by klaurent Peking

Kavli Affiliate: Zhuo Li | First 5 Authors: Tian-Qi Huang, Zhuo Li, , , | Summary: The Large High Altitude Air Shower Observatory (LHAASO) observed a dozen of gamma-ray sources with significant emission above 100 TeV, which may be strong candidates of PeVatrons. Neutrino observations are crucial to diagnose whether the gamma-ray radiative process is […]


Continue.. Neutrino Observations of LHAASO Sources: Present Constraints and Future Prospects

RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes

Posted by klaurent Chicago

Kavli Affiliate: Salman Habib | First 5 Authors: Salman Habib, Allison Beemer, Joerg Kliewer, , | Summary: In this work we propose RELDEC, a novel approach for sequential decoding of moderate length low-density parity-check (LDPC) codes. The main idea behind RELDEC is that an optimized decoding policy is subsequently obtained via reinforcement learning based on […]


Continue.. RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes

RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes

Posted by Chicago

Kavli Affiliate: Salman Habib | First 5 Authors: Salman Habib, Allison Beemer, Joerg Kliewer, , | Summary: In this work we propose RELDEC, a novel approach for sequential decoding of moderate length low-density parity-check (LDPC) codes. The main idea behind RELDEC is that an optimized decoding policy is subsequently obtained via reinforcement learning based on […]


Continue.. RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes

RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes

Posted by Chicago

Kavli Affiliate: Salman Habib | First 5 Authors: Salman Habib, Allison Beemer, Joerg Kliewer, , | Summary: In this work we propose RELDEC, a novel approach for sequential decoding of moderate length low-density parity-check (LDPC) codes. The main idea behind RELDEC is that an optimized decoding policy is subsequently obtained via reinforcement learning based on […]


Continue.. RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes

RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes

Posted by Chicago

Kavli Affiliate: Salman Habib | First 5 Authors: Salman Habib, Allison Beemer, Joerg Kliewer, , | Summary: In this work we propose RELDEC, a novel approach for sequential decoding of moderate length low-density parity-check (LDPC) codes. The main idea behind RELDEC is that an optimized decoding policy is subsequently obtained via reinforcement learning based on […]


Continue.. RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codes