Algorithmic Trading

• Deep Reinforcement Learning Automated Trading Agent
• Sequence to Sequence Recurrent Networks for Time Series Forecasting
• Portfolio Optimization and Visualization Real-Time Dashboard

Power Grid Optimization

• Deep Neural Network Power Consumption Forecasting
• Big Data Acquisition and Transformation Pipeline
• Deployment with Cloud-Native Microservices and Asynchronous Messaging Queue

Recommendation System

• Deep AutoEncoder User-Item Implicit Collaborashowtive Filtering
• Big Data Acquisition and Transformation Pipeline
• Admin Dashboard Integration and Customer Segmentation Visualization

KYC Identity Verification

• Optical Character Recognition OCR for Identity Card, Driving License, and Passport
• Face Detection, Recognition, and Matching Technologies.
• Deployment with Cloud-Native Microservices and Quantitative Performance Monitoring

Drop-Shipping Platform

• Development of E-Commerce Platform and Online Payment Gateway Integration
• Big Data Extraction, Aggregation and Transformation Pipeline
• Single Page Application Frontend

Product Image Recognition

• Deep Convolutional Network for Product Detection and Recognition
• Real-Time Model Training on New Images
• RESTful APIs Deployment with Model Training Admin Dashboard Development

Video Biomechanics Analysis

• Deep Learning Object Detection and Recognition
• Deep Learning Time Series Analysis and Forecasting
• Video Aggregation and Processing Cloud Pipeline

Cross-Validation Strategies for Time Series Forecasting

Time series modeling and forecasting are tricky and challenging. The i.i.d ( identically distributed independence ) assumption does not hold well to time series data.

How to become an expert in Computer Vision?

The question has been puzzling me for quite a while; How to become an expert in Computer Vision? And by an expert, I mean as a software engineer aka developer.

Useful Resources for Quantum Computing

Quantum Computing & Quantum Information is the promising future of Computer Science. Quantum Computing is making a disruption in areas such as Cryptography.

Quantum Finance: Quantum Computing Applications ...

Computer algorithms are inherent in every aspect of our daily lives without us noticing their existence. The smartphone in one’s pocket is thousands of times far more.

Artificial Intelligence: The History of Self-Driving Cars ...

The self-driving car industry is now one of the very hottest trends, causing a loud buzz not only in academia and industry but also from a socio-economic perspective.

Objective Functions in Deep Learning

In this report, I shall summarize the objective functions ( loss functions ) most commonly used in Machine Learning & Deep Learning.

Artificial Intelligence, Smart Cities & Intelligent Water in MENA

Water is one of our most precious natural resources, yet its availability has been severely impacted by the industrial revolution and resulting climate changes.

Synopsis of GraphGAN

GraphGANs are constituted of a Generator that is learning the underlying connectivity distribution between vertices as P(V|v_c) and a Discriminator

Synopsis of MGAN

Markovian Generative Adversarial Networks (MGANs) capture the feature statistics of Markovian Patches and generate images of arbitrary dimensions.

Synopsis of LeakGAN

Combining Reinforcement Learning with Generative Adversarial Networks has been applied to many problems such as drug discovery and text generation.

Synopsis of MaskGAN

MaskGAN allows the end-user to edit a segmentation mask which is used as a condition to apply face style manipulations interactively.

Revelations of Medieval Art with Image Processing and ML

Once we start believing that we understand our history, a new breakthrough reveals unexpected secrets. Taking historical facts for granted is no longer our only choice.

Objective Functions in Deep Learning

Design and analysis cost functions for training deep learning models.

Bank Marketing Data Preprocessing

Perform data engineering on bank marketing dataset using Python, Pandas, and MatplotLib.

LeNet5 using PyTorch

Implement Convolutional Neural Networks (CNN) as per LeNet5 for Handwritten digits recognition.

Classification on Kaggle Titanic Dataset

Implement a deep learning classifier on Kaggle using Python.

Python SciKit-Learn Regression Analysis

Implement and evaluate different regression analysis techniques using Python and SciKit-Learn.

IoT Communication Protocols

Demonstrate different IoT communication protocols such as MQTT and CoAP using Arduino, ESP8266, and Rasperry Pi Gateway.

Support Vector Machines

Simplified mathematical derivation of Support Vector Machines (SVM) classifiers and different kernel functions.

PyTorch Automation [Auf Deutsch]

Expose PyTorch model training and evaluation via RESTful APIs.

Drug Discovery using Deep Learning

A talk about drug discovery techniques using deep learning, reinforcement learning, and generative adversarial networks (GANs).