MortadhaMannai
XAI isn't just about revealing the 'why' behind AI decisions; it's about fostering a bridge of trust between humans and machines.
Saint Mary’s University Halifax, Nova scotia ,canada
Pinned Repositories
A-SHIP-OR-AN-ICEBERG-CAN-YOU-DECIDE-FROM-SPACE-
The remote sensing systems used to detect icebergs are housed on satellites over 600 kilometers above the Earth. The Sentinel-1 satellite constellation is used to monitor Land and Ocean. Orbiting 14 times a day, the satellite captures images of the Earth's surface at a given location, at a given instant in time. The C-Band radar operates at a frequency that "sees" through darkness, rain, cloud and even fog. Since it emits it's own energy source it can capture images day or night. Satellite radar works in much the same way as blips on a ship or aircraft radar. It bounces a signal off an object and records the echo, then that data is translated into an image. An object will appear as a bright spot because it reflects more radar energy than its surroundings, but strong echoes can come from anything solid - land, islands, sea ice, as well as icebergs and ships. The energy reflected back to the radar is referred to as backscatter. Here we see challenging objects to classify. We have given you the answer, but can you automate the answer to the question .... Is it a Ship or is it an Iceberg?
BERT-Neural-Language-Interface-Explainability-Explorer
Welcome to the Neural Language Interface (NLI) Explain project! This repository is dedicated to exploring and explaining the decision-making process of BERT models in the context of Natural Language Inference (NLI) tasks. We employ Feature Interaction methods to shed light on why BERT makes specific predictions in NLI.
Comparative-Analysis-of-Equity-Crowdfunding-Expenditure-Across-OECD-Nations-Python-and-R-Approach
This project aims to perform a comprehensive analysis of the differences in money spent on "Equity Crowdfunding" projects across OECD countries.
Disaster-Risk-Monitoring-Using-Satellite-Imagery-and-Nvidia-Libraries
Learn how to build and deploy a deep learning model to automate the detection of flood events using satellite imagery. This workflow can be applied to lower the cost, improve the efficiency, and significantly enhance the effectiveness of various natural disaster management use cases.
EvolveGCN-Evolving-Graph-Convolutional-Networks-for-Dynamic-Graphs-
This repository contains the code for EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs, published in AAAI 2020.
Fake-news-detection-with-LSTMs-and-BERT
well Social media has affected society during the last decade by providing free milieus for everyone to share their thoughts, ideas, and also news. As a negative effect, these environments have been used for propagation of low-quality, content-bare, and even outright “Fake” news. Spreading of Fake news has extreme effects on people’s minds and societies, such as decreasing one’s trust to all sources of news, making readers defensive against most news channels,The Fight Against Fake News with Deep Learning Fake news detection with LSTMs and BERT etc. This is why recently the detection of Fake news has become one of the top trends in the field of research. Referring to one of the latest works on this area, detecting Fake news in social media has exclusive features which cannot be found in traditional methods and approaches for reality detection so this work represent
Graph-Convolution-over-Pruned-Dependency-Trees-for-Relation-Extraction
Graph Convolution over Pruned Dependency Trees for Relation Extraction" is a sophisticated approach that leverages graph convolutional networks (GCNs) on pruned dependency trees to enhance the accuracy of relation extraction tasks
Housing-Prices-prediction
it's my personal work for Week 1Assignment Housing Prices: ( from coursera course :Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning)..In this exercise Itry to build a neural network that predicts the price of a house according to a simple formula. Imagine that house pricing is as easy as: A house has a base cost of 50k, and every additional bedroom adds a cost of 50k. This will make a 1 bedroom house cost 100k, a 2 bedroom house cost 150k etc. I create a neural network that learns this relationship so that it would predict a 7 bedroom house as costing close to 400k etc. Hint: my network might work better if i scale the house price down. i don't have to give the answer 400...it might be better that i created something that predicts the number 4, and then the answer is in the 'hundreds of thousands' etc.
Natural-Language-Processing-Analyzing-GitHub-Pull-Requests
This project covers the concepts of : Topic Modelling using LDA Clustering through tf-idf and BoW Dimension reduction through t-SNE and truncated SVD Classification and Regression algorithms
VOCAL-TRACK-EXTRACTION-USING-NEURAL-NETWORKS
There are four models in this project: Deep Clustering Model, Hybrid Deep Clustering Model, U-net Model and UH-net Model. Models are trained on DSD100 dataset. The project is based on PyTorch.
MortadhaMannai's Repositories
MortadhaMannai/Implementing-Callbacks-in-TensorFlow-using-the-MNIST-Dataset
classification using Fashion MNIST, a data set containing items of clothing. There's another, similar dataset called MNIST which has items of handwriting -- the digits 0 through 9. Write an MNIST classifier that trains to 99% accuracy and stops once this threshold is achieved. In the lecture you saw how this was done for the loss but here you will be using accuracy instead. Some notes: Your network should succeed in less than 9 epochs. When it reaches 99% or greater it should print out the string "Reached 99% accuracy so cancelling training!" and stop training. If you add any additional variables, make sure you use the same names as the ones used in the class. This is important for the function signatures (the parameters and names) of the callbacks.
MortadhaMannai/Housing-Prices-prediction
it's my personal work for Week 1Assignment Housing Prices: ( from coursera course :Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning)..In this exercise Itry to build a neural network that predicts the price of a house according to a simple formula. Imagine that house pricing is as easy as: A house has a base cost of 50k, and every additional bedroom adds a cost of 50k. This will make a 1 bedroom house cost 100k, a 2 bedroom house cost 150k etc. I create a neural network that learns this relationship so that it would predict a 7 bedroom house as costing close to 400k etc. Hint: my network might work better if i scale the house price down. i don't have to give the answer 400...it might be better that i created something that predicts the number 4, and then the answer is in the 'hundreds of thousands' etc.
MortadhaMannai/A-SHIP-OR-AN-ICEBERG-CAN-YOU-DECIDE-FROM-SPACE-
The remote sensing systems used to detect icebergs are housed on satellites over 600 kilometers above the Earth. The Sentinel-1 satellite constellation is used to monitor Land and Ocean. Orbiting 14 times a day, the satellite captures images of the Earth's surface at a given location, at a given instant in time. The C-Band radar operates at a frequency that "sees" through darkness, rain, cloud and even fog. Since it emits it's own energy source it can capture images day or night. Satellite radar works in much the same way as blips on a ship or aircraft radar. It bounces a signal off an object and records the echo, then that data is translated into an image. An object will appear as a bright spot because it reflects more radar energy than its surroundings, but strong echoes can come from anything solid - land, islands, sea ice, as well as icebergs and ships. The energy reflected back to the radar is referred to as backscatter. Here we see challenging objects to classify. We have given you the answer, but can you automate the answer to the question .... Is it a Ship or is it an Iceberg?
MortadhaMannai/Best_AI_paper_2020
A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code
MortadhaMannai/solutions
Solutions for projects.