Asiful Arefeen
Asiful Arefeen
Home
Posts
Projects
Talks
Publications
Contact
Light
Dark
Automatic
Recent & Upcoming Talks
2023
Entropy-based Logic Explanations of Neural Networks
This research paper aims at building an entropy layer for end-to-end explainable AI framework. Unlike LIME and Grad-CAM, Entropy Net does not rely on any auxuliary tool/model to explain its predictions. Also, Entropy Net focuses on downsizing the concepts required to explain predictions.
May 4, 2023 2:00 PM — 2:40 PM
Online (Zoom)
asiful-arefeen
PDF
Slides
Rep-Net: Efficient On-Device Learning via Feature Reprogramming
REP-Net is a counter to traditional transfer learning for On-board model training with more focus on memory efficiency.
Apr 6, 2023 2:00 PM — 2:30 PM
Online (Zoom)
asiful-arefeen
PDF
Slides
Training Generative Adversarial Networks with Limited Data
Training GANs require large amount of data. If tried with small datasets, the discriminator often times overfit producing meaningless feedback to the generator. One solution to training GANs with smaller dta could be using adaptive data augmentation.
Feb 23, 2023 2:00 PM — 2:40 PM
Online (Zoom)
asiful-arefeen
PDF
Slides
Domain Knowledge Aided Explainable Artificial Intelligence for Intrusion Detection and Response
Including domain knowledge can increase explainability without compromising on model performance. This paper mainly discusses a preprocessing technique to incorporate domain knowledge in a way they become very useful for explaining model’s predictions.
Feb 1, 2023 12:30 PM — 1:00 PM
Online (Zoom)
asiful-arefeen
PDF
Slides
2022
Augmented Experiment in Material Engineering Using Machine Learning
Incorporating domain knowledge to neural networks is a creative and case specific approach. This paper modifies the loss function of a fully-connected network with domain knowledge from kinetics which helped the model make precise prediction in its regression task.
Dec 21, 2022 3:00 PM — 3:45 PM
Online (Zoom)
asiful-arefeen
PDF
Slides
Computational Framework for Sequential Diet Recommendation: Integrating Linear Optimization and Clinical Domain Knowledge
Optimizes change in consumed nutrients while driving users to their desired diet.
Nov 14, 2022 11:00 AM — 12:00 PM
Online (Zoom)
asiful-arefeen
PDF
Slides
Local Interpretable Model-Agnostic Explanations
LIME is a great tool for explaining the predictions made by a model. LIME can explain any model regardless of their type, it works by building a linear model on vicinity of the sample intended to be explained.
Oct 19, 2022 10:30 AM — 11:00 AM
Online (Zoom)
asiful-arefeen
PDF
Slides
Characterizing Decision Boundary for DNN on High Dimensional Data
Decision boundaries are imposible to be visualized in hogh dimensional feature sets. Instead of visualizing them, we can characterize them and make them useful.
Sep 7, 2022 10:00 AM — Sep 7, 2021 10:30 AM
Online (Zoom)
asiful-arefeen
PDF
Slides
Grad-CAM for Interpreting DNN Model Decisions
Neural networks have a bad reputations as they are treated like black boxes and lack interpretations on the results they make. Grad-CAM can slightly interprete what is driving the model to make a decision.
Jul 22, 2022 12:00 PM — 12:30 PM
Online (Zoom)
asiful-arefeen
PDF
Slides
Boosting Lying Posture Classification with Transfer Learning
Enhancement of accuracy for wrist-worn sensor based lying posture classification via transfer learning
Jun 10, 2022 12:00 PM — 12:30 PM
Zoom (Online)
asiful-arefeen
Slides
Optimizations in Sparse Coding
Optimization Algorithms to begin with Sparse Coding.
Apr 22, 2022 12:00 PM — 1:00 PM
Zoom
asiful-arefeen
Slides
2021
Variational Autoencoder
Brief explanation on variational autoencoder mechanism and comparison with traditional autoencoder.
Nov 29, 2021 4:00 PM — 5:00 PM
Zoom
asiful-arefeen
PDF
Slides
Recent Techniques in Semi-Supervised Learning
Exploring traditional GAN and semi-supervised GAN and identify key dissimilarities
Sep 27, 2021 4:00 PM — 5:00 PM
Zoom
asiful-arefeen
PDF
Slides
SNR- Sub-Network Routing for Flexible Parameter Sharing in Multi-Task Learning
Finding the best structure of a Multi-task Learning Network given a set of related/unrelated tasks
Aug 16, 2021 3:00 PM — 4:00 PM
Zoom
asiful-arefeen
PDF
Slides
Which Tasks Should Be Learned Together in Multi-task Learning?
Task relation assessment and setting MTL parameters according to task groups
Jun 21, 2021 3:00 PM — 3:30 PM
Zoom
asiful-arefeen
PDF
Slides
Anywidth Network
Modulate the width of the network efficiently
May 17, 2021 3:00 PM — 3:30 PM
Zoom
asiful-arefeen
PDF
Slides
Paper Review: Attention is All You Need.
Apr 5, 2021 10:00 PM — 10:30 PM
Online (Zoom)
asiful-arefeen
paper
slides
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
Mar 1, 2021 11:00 PM — 11:30 PM
Zoom
asiful-arefeen
paper
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Jan 11, 2021 3:00 PM
asiful-arefeen
PDF
2020
U-Net: Convolutional Networks for Biomedical Image Segmentation
Dec 9, 2020 9:00 AM
asiful-arefeen
PDF
Slides
Social and competition stress detection with wristband physiological signals
Sep 9, 2020 12:00 PM — 12:00 PM
asiful-arefeen
PDF
Cite
×