I am a passionate Computer Science Engineer and AI Researcher focused on developing robust, interpretable, and trustworthy intelligent systems for real-world impact.
My work primarily revolves around:
- 🤖 Trustworthy AI & AI Safety
- 🧠 Deep Learning & Machine Learning
- 👁️ Computer Vision & Medical Imaging
- 📊 Uncertainty Quantification
- 🔍 Explainable AI (XAI)
- 📈 Educational Data Mining
- ⚡ Efficient AI Systems & Reproducible Research
I enjoy building research-oriented AI systems that combine:
- Reliability
- Interpretability
- Scalability
- Real-world applicability
• Trustworthy AI
• Multi-Turn AI Systems
• AI Safety
• Explainable AI (XAI)
• Computer Vision
• Medical Image Analysis
• Deep Learning
• Uncertainty-Aware Machine Learning
• Educational Data Mining
• Statistical Learning
PyTorch • TensorFlow • Scikit-Learn • OpenCV
XGBoost • LightGBM • SHAP • NumPy
Pandas • Matplotlib • Conformal Prediction
Statistical Modeling • Explainable AI
Research focused on:
- Multi-turn reasoning trajectories
- Compositional safety analysis
- Failure pattern detection
- Trustworthy conversational AI systems
- AI trajectory-level safety analysis
- Reasoning consistency evaluation
- Safety-aware AI benchmarking
- Failure detection in conversational systems
🔗 Repository: https://github.com/ShakibulAkash/DCARS-Trajectory-Level-Detection-of-Compositional-Safety-Failures-in-Multi-Turn-AI-Systems
A research-oriented framework for reliable educational analytics using uncertainty-aware machine learning.
- Leakage-aware learning
- Conformal prediction
- Ensemble learning
- Reliability estimation
- Uncertainty quantification
- Explainable AI integration
🔗 Repository: https://github.com/ShakibulAkash
Medical imaging pipeline for brain tumor classification using deep neural networks and explainable AI methods.
- CNN architectures
- Medical image preprocessing
- Explainable AI visualization
- Deep feature extraction
- Medical image classification
| Project | Research Area | Technologies |
|---|---|---|
| DCARS | AI Safety & Multi-Turn Reasoning | Python, Deep Learning |
| Student Performance Prediction | Educational Data Mining | ML, Statistical Learning |
| Brain Tumor Detection | Medical Computer Vision | CNN, OpenCV, PyTorch |
| Explainable AI Systems | Trustworthy AI | SHAP, XAI |
| Deep Learning Frameworks | Computer Vision | PyTorch, TensorFlow |
- Publish impactful AI research
- Advance trustworthy AI systems
- Develop interpretable machine learning frameworks
- Contribute to open-source AI research
- Build scalable intelligent systems
- Research reliable and safe AI architectures
📧 Email: shakibulakash@gmail.com
“Building AI systems that are not only intelligent, but also reliable, interpretable, and safe for real-world impact.”
I enjoy transforming research ideas into practical AI systems
that combine innovation, reliability, and interpretability.
```