Search Results for author: Saeed Amizadeh

Found 7 papers, 2 papers with code

Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"

no code implementations ICML 2020 Saeed Amizadeh, Hamid Palangi, Oleksandr Polozov, Yichen Huang, Kazuhito Koishida

To address this, we propose (1) a framework to isolate and evaluate the reasoning aspect of VQA separately from its perception, and (2) a novel top-down calibration technique that allows the model to answer reasoning questions even with imperfect perception.

Graph Generation Question Answering +5

PDP: A General Neural Framework for Learning SAT Solvers

no code implementations25 Sep 2019 Saeed Amizadeh, Sergiy Matusevych, Markus Weimer

There have been recent efforts for incorporating Graph Neural Network models for learning fully neural solvers for constraint satisfaction problems (CSP) and particularly Boolean satisfiability (SAT).

Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach

1 code implementation10 Jun 2019 Gyeong-In Yu, Saeed Amizadeh, Sehoon Kim, Artidoro Pagnoni, Byung-Gon Chun, Markus Weimer, Matteo Interlandi

To this end, we propose a framework that translates a pre-trained ML pipeline into a neural network and fine-tunes the ML models within the pipeline jointly using backpropagation.


Learning To Solve Circuit-SAT: An Unsupervised Differentiable Approach

no code implementations ICLR 2019 Saeed Amizadeh, Sergiy Matusevych, Markus Weimer

Recent efforts to combine Representation Learning with Formal Methods, commonly known as the Neuro-Symbolic Methods, have given rise to a new trend of applying rich neural architectures to solve classical combinatorial optimization problems.

Combinatorial Optimization reinforcement-learning +1

PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers

4 code implementations5 Mar 2019 Saeed Amizadeh, Sergiy Matusevych, Markus Weimer

In this paper, we propose a generic neural framework for learning CSP solvers that can be described in terms of probabilistic inference and yet learn search strategies beyond greedy search.

The Bregman Variational Dual-Tree Framework

no code implementations26 Sep 2013 Saeed Amizadeh, Bo Thiesson, Milos Hauskrecht

Graph-based methods provide a powerful tool set for many non-parametric frameworks in Machine Learning.

Text Categorization

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