Search Results for author: Jia Zou

Found 12 papers, 3 papers with code

FGeo-HyperGNet: Geometry Problem Solving Integrating Formal Symbolic System and Hypergraph Neural Network

1 code implementation18 Feb 2024 Xiaokai Zhang, Na Zhu, Yiming He, Jia Zou, Cheng Qin, Yang Li, Zhenbing Zeng, Tuo Leng

The symbolic part is a formal system built on FormalGeo, which can automatically perform geomertic relational reasoning and algebraic calculations and organize the solving process into a solution hypertree with conditions as hypernodes and theorems as hyperedges.

Geometry Problem Solving Relational Reasoning

FGeo-DRL: Deductive Reasoning for Geometric Problems through Deep Reinforcement Learning

1 code implementation14 Feb 2024 Jia Zou, Xiaokai Zhang, Yiming He, Na Zhu, Tuo Leng

We built a neural-symbolic system, called FGeoDRL, to automatically perform human-like geometric deductive reasoning.

Language Modelling reinforcement-learning

FGeo-TP: A Language Model-Enhanced Solver for Geometry Problems

no code implementations14 Feb 2024 Yiming He, Jia Zou, Xiaokai Zhang, Na Zhu, Tuo Leng

The application of contemporary artificial intelligence techniques to address geometric problems and automated deductive proof has always been a grand challenge to the interdiscipline field of mathematics and artificial Intelligence.

Language Modelling

Serving Deep Learning Model in Relational Databases

no code implementations7 Oct 2023 Alexandre Eichenberger, Qi Lin, Saif Masood, Hong Min, Alexander Sim, Jie Wang, Yida Wang, Kesheng Wu, Binhang Yuan, Lixi Zhou, Jia Zou

Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains, sparking growing interest recently.

A Comparison of Decision Forest Inference Platforms from A Database Perspective

no code implementations9 Feb 2023 Hong Guan, Mahidhar Reddy Dwarampudi, Venkatesh Gunda, Hong Min, Lei Yu, Jia Zou

In addition, the relation-centric representation we proposed significantly improved netsDB's performance in handling large-scale models, while the model reuse optimization we proposed further improved netsDB's performance in handling small-scale datasets.

Fraud Detection Management

It's the Best Only When It Fits You Most: Finding Related Models for Serving Based on Dynamic Locality Sensitive Hashing

no code implementations13 Oct 2020 Lixi Zhou, Zijie Wang, Amitabh Das, Jia Zou

However, preparation of training data is often a bottleneck in the lifecycle of deploying a deep learning model for production or research.

Tensor Relational Algebra for Machine Learning System Design

no code implementations1 Sep 2020 Binhang Yuan, Dimitrije Jankov, Jia Zou, Yuxin Tang, Daniel Bourgeois, Chris Jermaine

This implementation abstraction provides little built-in support for ML systems to scale past a single machine, or for handling large models with matrices or tensors that do not easily fit into the RAM of an ASIC.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.