Transforming the field of deep learning and computer vision requires a multidisciplinary approach that combines robust data-driven methodologies with strong engineering capabilities. As an expert in this area, I have developed impactful solutions to complex challenges in classification, segmentation, and reconstruction.
Key Expertise
* Boosting for enhanced model performance
* Computer Vision for accurate image analysis
* CUDA for optimized GPU acceleration
* Deep Learning (CNN, GAN) for sophisticated pattern recognition
* Docker for streamlined deployment and testing
* GIT for version control and collaboration
* Machine Learning (SVM) for predictive modeling
* NumPy for efficient numerical computations
* Pandas for data manipulation and analysis
* Python (TensorFlow, PyTorch, Scikit-Learn) for flexible development and prototyping
* SQL (MySQL, SQL Server, SQLite) for reliable database management
* Transformer for state-of-the-art language models
* XGBoost for scalable and interpretable boosting
Professional Experience Highlights
PhD Researcher at Achieving Clinical Excellence
* Developed an unsupervised deep framework under the CT imaging principle using inherent physics domain consistency to address unavailable ground truth problems in clinics.
* Proposed evaluating algorithm indirectly by subsequent segmentation to prove clinical effectiveness.
* Collaborated with researchers exploring domain consistency from experiments and published a technical paper.
* Designed a framework eliminating drawbacks of imbalanced data to increase true positives and false negatives simultaneously.
* Analysed tubular airway tree from a topological view and designed/implemented differentiated distance map and surface loss functions to improve clinically important metrics.
* Presented research outcomes at an international conference.
Academic Tutor at Educating Future Leaders
* Conducted machine/deep learning, computer vision, and data analysis tutorials in accessible terms, adapting to diverse student skill levels.
* Communicated with each student in the classroom to encourage participation and create a welcoming environment.
M.E. Researcher at Innovative Solutions for Brain Tumour Segmentation
* Designed a deep learning method addressing multi-modality image merge to utilize data effectively.
* Designed a multi-level decoder to enlarge the scale of the network and avoid training collapse problems.
* Participated in the BraTs Challenge, achieving top-rank performance and publishing two technical papers.
Algorithm Engineer at Advancing Deep Learning Technologies
* Deployed deep learning algorithms and debugged our quantization algorithm (Python) to improve robustness and tested the performance of algorithms provided by customers on our chip.
* Developed the chip simulation (C programming) and conducted bit-true with IC engineers to verify the correctness of chip design.
Software Engineer at Delivering Scalable Solutions
* Packaged the algorithms of our group under the API guidelines (Python) and deployed algorithms to the standard platform.
* Analysed data source, format, and size in various clinical environments to make our algorithm work.