Smith Washington
Arauco Canchumuni
Peruvian
Computer Science Specialist
Senior AI Scientist with over four years of experience, a specialist in machine learning/deep learning, generative models, data assimilation, and inverse problems.
- Development Manager, Applied Computational Intelligence Laboratory in Pontifical Catholic University of Rio de Janeiro.
- Professor of Computer Science, Data Science and Computer Engineering, Pontifical Catholic University of Rio de Janeiro.
- Senior Programmer in python, C, C++, C#, R and matlab
Experience in this institute:
- Computer Vision
- Deep Learning
Experience in this institute:
- Deep Learning Institute Platform
Experience in this university:
- Artificial Intelligence
- Machine Learning
- Deep Learning
- Computer Vision
- Data Science
- Data Assimilation
- Inverse problem
Experience in this university:
- Robotics
- Simultaneous Localization and Mapping (SLAM)
- Evolutionary Computation
Experience in this university:
- Pneumatic
- Electric Automation Technology
- Automation
- Programmable Logic Controller (PLC)
- SCADA System
Experience in this university:
- Robotics
- Control Systems
- Logic programming
- Sensors & Actuators
- Automation
- Spanish [Native]
- English [Professional]
- Portuguese [Professional]
Development Manager
Development projects in
- Artificial Intelligence
- Machine Learning
- Deep Learning
- Data Science
- History Matching
- Reservoir Simulations
- Distributed Systems
- Genetics Algorithms
PhD. Thesis - Hybrid Method Based into Kalman Filter and Deep Generative Model to History Matching and Uncertainty Quantification of Facies Geological Models.
MSc dissertation - Probabilistic Simultaneous Localization and Mapping of Mobile Robots in Indoor Environments with a Laser Range Finder.
Experience in this company:
- Control theory
- Mobile Robotics
These are all the articles I wrote.
Deep learning for mapping rainwater drainage networks using Remote Sensing Data.
Seismic Facies Segmentation Using Atrous Convolutional-LSTM Network.
Towards a Benchmark for Sedimentary Facies Classification- Applied to the Netherlands F3 Block.
Automatic Lithofacies Classification with t-SNE and K-Nearest Neighbors Algorithm.
History matching geological facies models based on ensemble smoother and deep generative models.
Smart Well Data Generation via Boundary-Seeking Deep Convolutional Generative Adversarial Networks.
The use of simuation to model the dispatch of inbound contaoners in port terminals.
Integration of Ensemble Data Assimilation and Deep Learning for History Matching Facies Models.
- Dog Lover
- Reading
- Play Soccer