Application-Based Deep Learning with PyTorch
Application-Based Deep Learning with PyTorch


Deep learning has numerous applications in real life. As one example, I recently conducted research on building damage assessment in satellite imagery using convolutional neural networks, which is explained briefly here:

Natural disasters ravage the world's cities, valleys, and shores on a monthly basis. Having precise and efficient mechanisms for assessing infrastructure damage is essential to channel resources and minimize the loss of life. Using a dataset that includes labeled pre- and post- disaster satellite imagery, we train multiple convolutional neural networks to assess building damage on a per-building basis. In order to investigate how to best classify building damage, we present a highly interpretable deep-learning methodology that seeks to explicitly convey the most useful information required to train an accurate classification model. We also delve into which loss functions best optimize these models. Our findings include that ordinal-cross entropy loss is the most optimal loss function to use and that including the type of disaster that caused the damage in combination with a pre- and post-disaster image best predicts the level of damage caused. Our research seeks to computationally contribute to aiding in this ongoing and growing humanitarian crisis, heightened by climate change.

In this talk, I intend to demonstrate how deep learning can be used in applications, using technologies like PyTorch and OpenCV within the Python programming language. I will go over how I conducted my research, but also delve into other ways in which deep learning can be used in application-based ways. AI for Social Good is a rising phenomenon and I want to ensure that researchers and industry professionals are inspired to use machine learning and deep learning for good.


Thomas Chen is an early-career machine learning researcher from New Jersey that is passionate about machine learning, computer vision, and artificial intelligence. He is highly involved in science research, especially in applying ML and AI to real-world issues that face society (e.g. deep learning-based computer vision for damage assessment post-natural disaster). He has presented his work at workshop sessions at high-level conferences such as NeurIPS, and is an invited speaker at numerous conferences like the IEEE Conference on Technologies for Sustainability and the Energy Anthropology Network.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google