Tus tareas
Acquire training in CNN convolutional networks at SENSIA's AI division.
Data collection and pre-processing:
-Acquire thermal imaging datasets.
-Perform data pre-processing, which could include image normalization, contrast adjustment, and segmentation if necessary.
Collaborate in the design and updates of CNN architectures in SENSIA:
-Adjust architecture as needed, considering factors such as network depth, filter size, and fully connected layers.
Training/Evaluation and Optimization of SENSIA models:
-Launch training scripts programmed in Python or C++ using SENSIA's AI servers.
-Evaluate model performance using the validation and test suite.
-Consider data augmentation techniques to increase the variability of the training set.
Monitoring and Maintenance:
-Establish a monitoring system to track the performance of the model in production.
-Update the model as necessary to adapt to changes in data or application requirements.
Research and Continuous Development:
-Keep up to date on the latest research and developments in CNN as applied to thermal imaging.
-Explore new techniques and approaches to constantly improve model performance.
-Collaborate in future agreements with Universidad Carlos III de Madrid.
Interaction with Customers and End Users:
-Maintain effective communication with customers and end users to understand their needs and receive feedback on model effectiveness.
-Provide technical assistance and resolve queries related to the implementation and use of AI models.
Data collection and pre-processing:
-Acquire thermal imaging datasets.
-Perform data pre-processing, which could include image normalization, contrast adjustment, and segmentation if necessary.
Collaborate in the design and updates of CNN architectures in SENSIA:
-Adjust architecture as needed, considering factors such as network depth, filter size, and fully connected layers.
Training/Evaluation and Optimization of SENSIA models:
-Launch training scripts programmed in Python or C++ using SENSIA's AI servers.
-Evaluate model performance using the validation and test suite.
-Consider data augmentation techniques to increase the variability of the training set.
Monitoring and Maintenance:
-Establish a monitoring system to track the performance of the model in production.
-Update the model as necessary to adapt to changes in data or application requirements.
Research and Continuous Development:
-Keep up to date on the latest research and developments in CNN as applied to thermal imaging.
-Explore new techniques and approaches to constantly improve model performance.
-Collaborate in future agreements with Universidad Carlos III de Madrid.
Interaction with Customers and End Users:
-Maintain effective communication with customers and end users to understand their needs and receive feedback on model effectiveness.
-Provide technical assistance and resolve queries related to the implementation and use of AI models.