Abdullah Mamun
Abdullah Mamun
Home
Publications
Experience
Talks
News
Contact
CV
Light
Dark
Automatic
Recent & Upcoming Talks
2023
Towards A Rigorous Science of Interpretable Machine Learning
In this position paper, the authors define interpretability and describe when interpretability is needed (and when it is not). Next, they suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.
Aug 23, 2023 1:30 PM — 3:00 PM
Health Futures Center, ASU
Abdullah Mamun
PDF
Invited talk: Time-Series Wearable Activity Forecasting
This research aimed to develop a lifestyle intervention system with an emphasis on time series forecasting and also to develop a generic multimodal activity forecasting scheme that can be used with either early fusion or late fusion mechanisms.
Apr 14, 2023 11:30 AM — 11:50 AM
La Sala Ballroom, ASU West Campus
Abdullah Mamun
slides
Time Series Data Augmentation for Deep Learning: A Survey
This paper provides an overview of basic and advanced approaches of time-series data augmentation.
Mar 9, 2023 2:00 PM — 2:00 PM
Online (Zoom)
Abdullah Mamun
PDF
slides
Language Models are Few-Shot Learners
This paper proposes GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting.
Feb 15, 2023 12:30 PM — 1:00 PM
Online (Zoom)
Abdullah Mamun
PDF
slides
Masked Autoencoders Are Scalable Vision Learners
This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision.
Jan 11, 2023 12:00 PM — 12:30 PM
Online (Zoom)
Abdullah Mamun
PDF
2022
Reinforcement Learning for Solving the Vehicle Routing Problem
A reinforcement learning approach to solve the vehicle routing problem.
Nov 23, 2022 12:00 PM — 12:30 PM
Online (Zoom)
Abdullah Mamun
PDF
slides
Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
This paper addresses the generalization gap on large neural networks with adaptive gradient-based optimizers and proposes a partially adaptive solution to overcome the problem.
Oct 5, 2022 12:00 PM — 12:30 PM
Online (Zoom)
Abdullah Mamun
paper
Multimodal Time-Series Activity Forecasting for Adaptive Lifestyle Intervention Design
We focus on devising algorithms that combine data about physical activity and engagement with the app to predict future physical activity performance.
Aug 31, 2022 12:00 PM — 12:30 PM
Online (Zoom)
Abdullah Mamun
PDF
slides
ViViT: A Video Vision Transformer
Jul 1, 2022 12:00 PM — 12:30 PM
Online (Zoom)
Abdullah Mamun
paper
A Review of Approximate Dynamic Programming and Feature-based Aggregation
May 6, 2022 12:00 PM — 12:30 PM
Online (Zoom)
Abdullah Mamun
paper(Powell)
paper(Bertsekas)
Multiagent Rollout Algorithms and Reinforcement Learning
Apr 8, 2022 10:00 PM — 10:30 PM
Online (Zoom)
Abdullah Mamun
paper
slides
2021
From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba
Oct 11, 2021 10:00 PM — 10:30 PM
Online (Zoom)
Abdullah Mamun
paper
slides
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
Aug 23, 2021 10:00 PM — 10:30 PM
Online (Zoom)
Abdullah Mamun
paper
slides
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
Jun 28, 2021 10:00 PM — 10:30 PM
Online (Zoom)
Abdullah Mamun
paper
slides
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
May 10, 2021 10:00 PM — 10:30 PM
Online (Zoom)
Abdullah Mamun
paper
slides
Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
Apr 12, 2021 3:00 PM
Pullman, WA
Abdullah Mamun
PDF
Code
Slides
The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
Mar 8, 2021 3:00 PM
Pullman, WA
Abdullah Mamun
PDF
Slides
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
Feb 1, 2021 3:00 PM
Pullman, WA
Abdullah Mamun
PDF
Slides
Cite
×