AloshkaD
Senior Data Scientist at Microsoft. Multi AI agent reasoning researcher. Robotics software and perception engineer. Data scientist and inventor. Beekeeper.
MicrosoftPaloAlto, CA
Pinned Repositories
AI_activity_recognition-
AI_Agent_Trader
Multi AI Agent Collaboration for Trending Stock Financial Analysis
AndroidUAVGS
This project is for testing a simple Android App to connect to the Pixhawk
Autonomous_SDC
Find lane lines and draw a solid line to localize a self-driving car on the road. I used image processing techniques and Haugh transform
DroneTracking
leetcode_assistant
LeetCode Coding multi-agent AI Assistant with LangGraph and Graph reasoning
localGPT-Vision
Chat with your documents using Vision Language Models. This repo implements an End to End RAG pipeline with both local and proprietary VLMs
P5_object_tracking
This project was developed for identifying vehicles in a video stream. The project is a corner stone for a real time vehicle tracking algorithm that employ semantic pixel-wise methods. This project solves the tracking problem for the Udacity final project in a different way that the general approach presented in the course. Instead of using the HOG features and other features extracted from the color space of the images, we used the U-Net[1] which is a convolutional network for biomedical image segmentation.
Realtime_AI_Assistant
Code for my cutting-edge multi-agent systems with advanced cognitive capabilities: Architecting AI agents using multi-modal graph reasoning for enhanced decision-making. Implementing neural-symbolic approaches to emulate and augment human-like intelligence Designing predictive models to evaluate multiple future outcomes for optimal agent choices.
SDCar_software_p3
Train a car how to drive using human driving behavior. it uses tensorflow, keras, and image augmentation.
AloshkaD's Repositories
AloshkaD/adv_attack_capsnet
Tensorflow Implementation of Adversarial Attack to Capsule Networks
AloshkaD/AirSim
Open source simulator based on Unreal Engine for autonomous vehicles from Microsoft AI & Research
AloshkaD/Arnold
Arnold - DOOM Agent
AloshkaD/CarND-Capstone
AloshkaD/CarND-Capstone-1
AloshkaD/cocostuff
The official homepage of the COCO-Stuff dataset.
AloshkaD/deep-reinforcement-learning
Repo for the Deep Reinforcement Learning Nanodegree program
AloshkaD/Deep_reinforcement_learning_Course
Implementations from the free course Deep Reinforcement Learning with Tensorflow
AloshkaD/DeepSolar
Nationwide houseshold-level solar panel identification with deep learning
AloshkaD/Delving-deep-into-GANs
:mag: A curated list of Generative Adversarial Networks (GANs) resources sorted by reputation
AloshkaD/DenseNet-Keras
DenseNet Implementation in Keras with ImageNet Pretrained Models
AloshkaD/Drone-Hover-RL
A hover system for Microsoft AirSim using reinforcement learning (Q-learning and SARSA)
AloshkaD/GAN-Pokemon
GAN network example using Pokemon
AloshkaD/gcg
AloshkaD/kaggle-imaterialist
The First Place Solution of iMaterialist (Fashion) 2019 at FGVC6
AloshkaD/kaggle_salt_bes_phalanx
Kaggle Salt b.e.s. & phalanx
AloshkaD/keras-deeplab-v3-plus
Keras implementation of Deeplab v3+ with pretrained weights
AloshkaD/Keras-GAN
Keras implementations of Generative Adversarial Networks.
AloshkaD/keras-rl
Deep Reinforcement Learning for Keras.
AloshkaD/magenta
Magenta: Music and Art Generation with Machine Intelligence
AloshkaD/mmdetection_object_detection_demo
How to train an object detection model with mmdetection
AloshkaD/Move_37_Syllabus
This is the syllabus for "Move 37", Siraj Raval's new course at School of AI
AloshkaD/PixelDCN
Implementation of Pixel Deconvolutional Networks
AloshkaD/pretrained_models
AloshkaD/SegCaps
A Clone version from Original SegCaps source code with enhancements on MS COCO dataset.
AloshkaD/softlearning
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.
AloshkaD/sonic_contest
Source code for OpenAI Retro Contest for Sonic the Hedgehog
AloshkaD/stable-baselines
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
AloshkaD/TheSpaghettiDetective
AI-based failure detection for 3D printer remote management and monitoring.
AloshkaD/USBuildingFootprints
Computer generated building footprints for the United States