International Conference on Computer and Knowledge Engineering

Home / 12th International Conference on Computer and Knowledge Engineering

Dual Memory Structure for Memory Augmented Neural Networks for Question-Answering Tasks

Authors :

Amir Bidokhti¹ Shahrokh Ghaemmaghami²

1- Department of Electrical Engineering. Sharif University of Technology. Tehran, Iran 2- Sharif University of Technology

Keywords :

deep learning،memory augmented neural networks،graph neural networks،question-answering،neural Turing machine

Abstract :

Memory is crucial for machine learning tasks on sequential data. From vanilla RNN to LSTM and memory augmented neural networks, researchers have investigated several types of memory structures. However, they suffer from limitations in the capacity or ability to keep track of long-term dependencies. This paper presents an external memory module composed of two distinct submodules that are inspired by memory in the human brain. Besides, a sleep mechanism is incorporated into this memory, which can mimic sleep's effects on improving human memory. The proposed method is fully differentiable; thus, backpropagation can be used for its training. Experiments conducted on the bAbI dataset show that the proposed method is successful in 16 out of 20 tasks, and the average error is 2.8%. The performance of the proposed method is far better than the conventional NTM, and it has the lowest prediction error in 7 out of 20 tasks among baseline systems. Besides, the proposed system is the only system that can solve tasks 16 and 17 of the bAbI dataset.

Papers List

List of archived papers

Introducing Meta-Contrastive Adaptive Autoencoder to Tackle Cold-Start Challenges in Sparse Domains

Hossein Rashid - Erfan Arzhmand - Fatemeh Hosseini

Using Deep Learning for Classification of Lung Cancer on CT Images in Ardabil Province

Mohammad Ali Javadzadeh Barzaki - Jafar Abdollahi - Mohammad Negaresh - Maryam Salimi - Hadi Zolfeghari - Mohsen Mohammadi - Asma Salmani - Rona Jannati - Firouz Amani

LightFedSelect: A Lightweight Framework for Byzantine-Robust Federated Learning

Seyed Saeed Razavi - Seyed Arsalan Vasegh Rahim Parvar - Soroosh Dadashi Pakdeh - Mohammad Matin Rezaeifard - Morteza Mollaie Chafi - Reza Ebrahimi Atani

Generating Hand-Written Symbols With Trajectory Planning Using A Robotic Arm

Arya Parvizi - Armin Salimi-Badr

Attention Transfer in Self-Regulated Networks for Recognizing Human Actions from Still Images

Masoumeh Chapariniya - Sara Vesali Barazande - Seyed Sajad Ashrafi - Shahriar B.Shokouhi

Predicting the Recovery Rate of COVID-19 Using a Novel Hybrid Method

Fatemeh Ahouz - Ebrahim Sayahi

FedBrain-Distill: Communication-Efficient Federated Brain Tumor Classification Using Ensemble Knowledge Distillation on Non-IID Data

Rasoul Jafari Gohari - Laya Aliahmadipour - Ezat Valipour

An Efficient Approach for Breast Abnormality Detection through High-Level Features of Thermography Images

Farhad Abedinzadeh Torghabeh - Yeganeh Modaresnia - Seyyed Abed Hosseini

Robust Distributed Learning over Heterogeneous Adaptive Networks based on Federated BSP Model

Fatemeh Barani - MohammadHafez Yari - Abdorreza Savadi - Hadi Sadoghi Yazdi

Multi-Layered Defense Against Modern Phishing: A Dual-Sandbox and CDR Approach

Mahdi Seyfipoor - Mohammad Mahdi Eskandari