Several areas of Earth with large accumulations of oil and gas also have huge deposits of salt below the surface. Salt bodies are known for their propensity to form nice oil traps. However, knowing where large salt deposits are precisely is very difficult. Professional seismic imaging still requires expert human interpretation of salt bodies. This leads to very subjective, highly variable renderings. More alarmingly, it leads to potentially dangerous situations for oil and gas company drillers. That's why the oil & gas industry is now employing AI-based approaches to automatically identify subsurface salt bodies. This presentation showcases how Deep Learning is used to scan underground seismic images, looking for potentially resource-rich areas.
Python code included and publicly available at:
https://github.com/neaorin/kaggle-tgs-challenge
23. 3
Error back propagation
Feedforward of information
Loss Function (L)
≠2
Optimizer
Gradient of the loss with respect
to each weight:
𝜕L
𝜕w
= ?
w11
w21
w31
Gradient Descent
𝜕L
𝜕w
46. Loss Function
Lovász Loss
The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in
neural networks https://arxiv.org/abs/1705.08790
https://github.com/bermanmaxim/LovaszSoftmax
More than a year ago we unified our research and engineering organizations into AI&R. We started with XX number of people, and we are XX. Huge investment.
However we have to do a similar effort in going to market. That’s why [click] we just announced a marketing organization that I will be leading to (1) help productizing the amazing work created by the combination of Engineering and Organization in Harry Shum’s organization and (2) going to market to change the perception and drive broad awareness of that innovation.
I couldn’t be more excited to do so.
More than a year ago we unified our research and engineering organizations into AI&R. We started with XX number of people, and we are XX. Huge investment.
However we have to do a similar effort in going to market. That’s why [click] we just announced a marketing organization that I will be leading to (1) help productizing the amazing work created by the combination of Engineering and Organization in Harry Shum’s organization and (2) going to market to change the perception and drive broad awareness of that innovation.
I couldn’t be more excited to do so.
More than a year ago we unified our research and engineering organizations into AI&R. We started with XX number of people, and we are XX. Huge investment.
However we have to do a similar effort in going to market. That’s why [click] we just announced a marketing organization that I will be leading to (1) help productizing the amazing work created by the combination of Engineering and Organization in Harry Shum’s organization and (2) going to market to change the perception and drive broad awareness of that innovation.
I couldn’t be more excited to do so.
More than a year ago we unified our research and engineering organizations into AI&R. We started with XX number of people, and we are XX. Huge investment.
However we have to do a similar effort in going to market. That’s why [click] we just announced a marketing organization that I will be leading to (1) help productizing the amazing work created by the combination of Engineering and Organization in Harry Shum’s organization and (2) going to market to change the perception and drive broad awareness of that innovation.
I couldn’t be more excited to do so.
More than a year ago we unified our research and engineering organizations into AI&R. We started with XX number of people, and we are XX. Huge investment.
However we have to do a similar effort in going to market. That’s why [click] we just announced a marketing organization that I will be leading to (1) help productizing the amazing work created by the combination of Engineering and Organization in Harry Shum’s organization and (2) going to market to change the perception and drive broad awareness of that innovation.
I couldn’t be more excited to do so.