Derin Öğrenme Jobs

The project centres on building a production-ready medical image -classification pipeline that leverages modern deep-learning techniques. I have a labelled dataset and need end-to-end code that ingests the text, handles cleaning and tokenisation, and trains an accurate classifier. Python is the preferred language; The preprocessing must involve Quantum computing techniques using Pennylane. PyTorch, TensorFlow or another mainstream framework is fine as long as the solution is reproducible and easy to extend. Key deliverables: • Well-commented source code (data loading, model, training loop, evaluation) • Clear instructions to run training on a fresh machine (README or notebook) • Metrics report showing accuracy, precision, recall and F1 on a held-out set • Export...

AI & MACHINE LEARNING TRAINING MANUAL DEVELOPMENT We are urgently seeking a highly qualified Expert Trainer to develop a comprehensive, hands-on Manual and deliver specialized training to Customs of an African country. This project aims to enable the beneficiary organization to autonomously design, optimize, and deploy AI/ML solutions for risk management and customs clearance efficiency. Scope of Work: Develop curriculum and content focusing on advanced technical modules, including: Data Science & Machine Learning: Deep Learning and Python Data Science foundations. Generative AI & LLMs: Advanced Prompt Engineering, Fine-tuning, NLP/Transformers, and API Deployment (LangChain). Methodology: Emphasize practical application, real-world customs use cases, and Capstone projects (...

I am working on an academic research project focused on multi-cloud resource orchestration using a decentralized framework called IMACO (Intelligent Multi-Agent Cloud Orchestration). Currently, I have implemented a Python-based simulation system that includes: Task scheduling using real workload data (Google Cluster Workload Traces) Existing scheduling strategies: Round Robin (RR) Cost-based scheduling IMACO (adaptive rule-based scheduler) objective : I want to extend the system by implementing: 1. MAS-Cloud+ (Multi-Agent System) Each cloud provider should act as an independent agent Agents evaluate tasks using scoring logic (cost, latency, load, SLA) A coordinator selects the best agent for task allocation Output must match existing format for comparison 2. Reinforcement Learning Inte...

I am preparing a scientific-grade computer-science paper that explores how Artificial Intelligence can be applied to Disease Diagnosis, with a sharp focus on Genetic Disorders. I already have a broad outline but need a researcher-writer who can turn it into a publishable manuscript that meets typical IEEE or Springer journal standards. Here’s what I’m after: • Scope. A clear literature review on AI techniques currently used for diagnosing genetic conditions such as cystic fibrosis, sickle-cell, or rare chromosomal abnormalities. Contrast traditional pipelines with cutting-edge deep-learning approaches (CNNs, Transformers, multimodal models, etc.). • Original contribution. Either propose a novel framework or run a small-scale experimental study on an open dataset (...

Project Title AI-Powered Audio Analysis Software for Sleep Respiratory Detection & Snoring Classification Project Description I am looking for an expert in Audio Signal Processing and Machine Learning to develop a specialized software tool for analyzing 8-hour sleep audio recordings. The system must process audio data to identify, categorize, and log specific respiratory events using provided training datasets. 1. Detection & Classification Requirements The software must accurately detect and quantify the following: • Normal Breathing: Total event count. • Labored Breathing: Total event count. • Snoring Intensity Levels: o Low Snoring: 10 – 30 dB o Moderate Snoring: 30 – 50 dB o Heavy Snoring: 50 – 80 dB o Explosive Snoring: > 80 dB • Apneic...

I run several cooking blogs and want to automate the creation of clean, consistent ingredient photos. Your task is to train (or fine-tune) an image-generation model so that it reliably produces minimalistic ingredient shots laid out on a wooden surface. Here’s what I need from you: • Help me assemble, clean, and label a high-quality training set of ingredient images that match the desired look. • Select or build the best model architecture (Stable Diffusion, DreamBooth, or a comparable approach)—I’m open, as long as it learns quickly and can run locally after training. • Train and validate the model, then deliver the final weights, a straightforward inference script, and a short guide so I can generate new photos on demand (Python preferred). &bu...

• Description Video frames will be fed into the engine, and the backend API will return certain information: 1. Types of sports What sport is it? Football/basketball/rugby/American football, etc 2. List of Logos Detected logos: UEFA, Real Madrid, Bayern Munich, Liverpool, Inter, etc 3. List of players Identify players from the shirt: 10 Kylian Mbappe, 11 Rodrygo, 12, 13 … 4. Home/away From the players’ wears: Real Madrid home/away, Liverpool home/away 5. Match info (team and score) on the top left corner of the screen (if there is any) Upon a worker's initiation and processing, your engine will store the identified information in memory and send it back to the front end. The worker can be re-initiated/reused. For training purposes, there will be the following ...

Lütfen detayları görmek için Kaydolun ya da Giriş Yapın.

I need a complete Automatic Number Plate Recognition solution that accurately reads both car and motorcycle plates during daylight hours. Once a plate is captured, the system must do two things automatically: log the full plate data (image, text, timestamp) into a database and trigger an immediate alert through a simple webhook or REST call. My ideal stack is Python with OpenCV or a comparable vision framework, paired with a modern detection model such as YOLOv8-seg, but I am open to alternatives if you can demonstrate equal or better accuracy. You are free to use an off-the-shelf OCR engine (Tesseract, EasyOCR, PaddleOCR) or a custom-trained model, as long as you meet the accuracy target. Key deliverables • Optimized plate-detection and OCR pipeline tuned for daylight footage &bu...

Our client runs a call center with Nigerian agents calling US businesses. They need a Python script that makes the agents' accent sound more neutral and clear to American ears in real time during live phone calls. The hard part is already done. There is a fully built Node.js server that handles the live call audio. We just need you to write one Python script that plugs into it. What the script needs to do: Receive live audio from the server, process it through a voice conversion model to soften the Nigerian accent, and send the processed audio back. The whole process must happen in under 150ms so the conversation feels natural with no delay. Tech details: Audio comes in as mulaw 8kHz chunks. You can resample internally for better model performance then convert back before sending ...

Looking for a highly skilled Data Scientist with deep expertise in AI and Generative AI to lead cutting-edge retail merchandising and pricing analytics initiatives, driving scalable forecasting, optimization, and intelligent automation solutions. -Leverage state-of-the-art AI and Generative AI techniques to drive innovation in retail merchandising and pricing analytics. -Design, develop, and deploy advanced machine learning and optimization models to support data-driven business decisions. -Build scalable solutions for demand forecasting, assortment optimization, price elasticity modeling, and inventory allocation and replenishment. -Develop sophisticated demand forecasting systems using multivariate and hierarchical models for long-range, multi-echelon predictions. -Address complex f...

I’m assembling a small, highly-skilled development squad to finish a platform that sees the world, talks to external services that never published their docs, and then deploys itself at scale. Python sits at the heart of the codebase, so deep confidence with modern Python, virtual environments and dependency management is essential. Most of the heavy lifting in computer vision happens through OpenCV and complementary deep-learning libraries; the pipeline must handle object detection, image processing and facial recognition with equal reliability and speed. If you also think in C++ or Java when performance demands it, that flexibility will be welcome. Beyond vision, we have to collect data from third-party applications that do not provide friendly endpoints. That means reverse-e...

I have a proprietary image dataset and I need a seasoned computer-vision engineer to turn it into an end-to-end solution that can 1) recognise each image, 2) detect all relevant objects inside it, and 3) optionally segment those objects when that adds value to the overall result. The primary goal is accurate detection and classification, but I’d like the system to be flexible enough to switch on pixel-level segmentation whenever it boosts performance. Here is what I’m after: • A clean Python pipeline (PyTorch or TensorFlow preferred, with OpenCV for preprocessing) that ingests my custom images, trains suitable models, and exposes an easy inference script. • Clear evaluation: confusion matrices, mAP/IoU scores, and plots of loss/accuracy over epochs so I can judge...

Project Title AI-Powered Textile Design Processing Tool (Image-to-Layered PSD System) ⸻ Project Overview We are building an AI-powered system for the textile and digital printing industry that can convert high-resolution flattened images (e.g., garments on models) into fully editable layered files (PSD format). The goal is to enable textile manufacturers and designers to: • Extract individual design components (patterns, colors, textures) • Edit them independently in tools like Photoshop • Use outputs directly for production and printing workflows This project is focused on accuracy, scalability, and production-readiness, not just a demo-level solution. ⸻ Objective Develop a system that can: 1. Take a high-resolution input image (300 DPI, large dimensions) 2. A...

The AI Medical Diagnosis Chatbot is an intelligent healthcare assistance system developed using Machine Learning, Natural Language Processing (NLP), and Conversational AI technologies. The main objective of this project is to help users analyze symptoms, predict possible diseases, and generate preliminary medical guidance through a conversational chat interface. The chatbot interacts with users in a human-like manner by accepting symptom-related queries in natural language, such as fever, cough, headache, fatigue, or other health concerns. Using trained machine learning models, the system processes the user’s symptoms and predicts the most probable disease or medical condition. The project integrates NLP techniques to understand user input, extract symptoms, and convert them into a...

Building an AI-powered fetal ultrasound biometry analysis system. Looking for an experienced ML/computer vision engineer or team. The project involves developing a two-phase deep learning pipeline for automated measurement of fetal biometry from 2D ultrasound images. Ultrasound plane detection and classification (head, abdomen, femur planes) Semantic segmentation of anatomical structures using CNN/U-Net architecture Ellipse fitting and geometry extraction for biometry calculations Automated measurement of HC, BPD, AC, FL, OFD, EFW, and derived ratios Scan quality scoring, measurement consistency validation Basic explainability (GradCAM overlays) and rule-based report generation Training datasets: HC18, FETAL_PLANES_DB, FPUS23, INTERGROWTH growth charts Multi-task learning model (single bac...

I need an AI-driven workflow that ingests raw video (MP4/MOV) and automatically follows a chosen object through every frame, delivering a clean alpha-masked output I can drop straight into my edit. The goal is to save me from manual rotoscoping; accuracy and speed are both critical. Here’s how I picture the collaboration: you build or adapt a model—using tools such as PyTorch, TensorFlow, Detectron2, or a proven OpenCV pipeline—that detects the target, keeps the mask tight even during fast motion, and exports either a keyed video or a PNG sequence. A small sample clip will be provided for you to demonstrate proof of concept; once results look solid we’ll run the system on the full batch. Deliverables • Python or command-line script (with all dependencie...

I’m putting together a short marketing piece for our company website and I need a skilled video editor who can create a convincing deepfake face swap. The goal is to place our spokesperson’s face onto an actor so the final clip looks seamless, natural, and fully in-character with lip-sync and expressions matching perfectly. You should be comfortable working with deep-learning tools such as DeepFaceLab, FaceSwap, or equivalent custom workflows, then finishing the composite inside After Effects, Premiere Pro, or any similar suite for colour matching and final polish. Clean skin tones, consistent lighting, and frame-by-frame accuracy are critical because this video will represent our brand on a highly visible page. I’ll provide: • High-resolution source footage of bo...

AI Video Creator Needed (Realistic Club Scene) I’m looking for a skilled AI video creator or agency who can produce a highly realistic video using AI tools and editing techniques. Project Requirement: I need a video of a man dancing inside a nightclub while holding an alcohol bottle. The final output should look natural, cinematic, and as close to real footage as possible. Input I Will Provide: High-quality photos of the person Additional video clips (if required) to improve realism Expectations: Use advanced AI video tools (such as Runway ML, Pika Labs, HeyGen, or similar) Smooth and realistic motion (no glitches or distortions) Proper lighting and club atmosphere (lights, crowd vibe, effects) Natural body movement and face consistency Ability to enhance with manual editing if ne...

I'm seeking an expert in AI algorithm design to create a comprehensive bowling assistant. The algorithm should: - Predict ball trajectory - Analyze player performance - Suggest optimal bowling techniques Ideal candidates will have: - Strong background in AI and machine learning - Experience in sports analytics - Proven track record in algorithm design Please include relevant experience in your application. So professionals have ball reps who stand behind them. Suggest ball changes, scout lanes etc. What if we have an AI app that you can input your bowling balls, core, covers. Input your ball speed, axis tilt, pap etc. Input the lane condition bowling on and then input where you are standing what ball your threw and the result. You can say that ball didnt hook when I hit this mark...

I’m building an avatar-based podcast training series and I need a genetic-AI workflow that can transform any script I provide into a complete video module. The goal is simple: a realistic on-screen presenter narrates my content while the system automatically inserts engaging, interactive graphics and supporting video clips at the right moments. Here’s what matters most to me: • Interactive graphics and videos must steal the show—they should illustrate key concepts, animate data, and invite the viewer to click, pause, or explore. • Avatars must look realistic, lip-sync flawlessly, and be easy to re-skin for future episodes. • The entire pipeline—from text input to final MP4—should run with minimal manual tweaking, whether you build it in Pyt...

I’m launching a new training calendar and the first item on the list is an Artificial Intelligence & Machine Learning batch that must dive straight into advanced territory. The cohort already has solid foundations, so the sessions need to centre on Deep Learning—building, tuning and deploying neural-network models with real-world datasets. If you’re also comfortable branching into Reinforcement Learning or NLP later, that flexibility will be a plus for the longer roadmap, but the immediate priority is Deep Learning mastery. The sessions will be delivered live (online or hybrid can be arranged), and I’ll rely on you to: • Shape a clear, week-by-week syllabus covering CNNs, RNNs, transformers, optimisation tricks, model interpretability and MLOps basics usi...

I’m ready to turn a labelled image dataset into a production-ready machine learning model that reliably classifies each photo into the correct category. Your job is to design, train, and evaluate the full image-classification pipeline. You may build from scratch or fine-tune a proven architecture such as ResNet, EfficientNet, MobileNet, or a vision transformer—as long as the final model meets the accuracy targets we set together. Feel free to work in PyTorch or TensorFlow/Keras; I’m comfortable deploying either. What I’ll provide • A structured folder of training, validation, and test images • Category labels and a brief data dictionary • Access to a GPU instance if you need it What I need back 1. Clean, well-commented code (Jupyter notebook or...

The project centers on building a production-ready TensorFlow 2.x model that classifies tabular data delivered to us through an internal API. I have the API specifications and sample payloads ready; you will turn those streams into a clean training pipeline, engineer the right features, and iterate until the classifier meets our performance targets in real-world tests. Scope of work • Data pipeline – pull the API data, handle preprocessing, and produce TensorFlow-friendly datasets for train/val/test splits. • Model development – design, train, and tune a deep learning architecture suitable for tabular inputs (e.g., wide & deep, Transformer, or other proven structures). • Optimization – experiment with hyperparameters, regularization, and callback...