Pointers at Glance
- The Conundrum is a startup that optimizes the factory processes.
- One of the products that they have is the Conundrum Euler defects detection system, which is based on simulation data.
The company puts technology into manufacturing, where the team simulates defects and then uses them. The team styles transfer models to create neural networks that can detect real defects without any need to collect photos with real defects.
Conundrum is growing very fast. Currently, it has about 100 employees. Now, they are searching for new ways to expand the technology and move into various industries, finding industries where their technology can fit in.
The hardware is developing fast. The company gets access to cameras that can provide high resolution and detect problems or smaller defects. They have more access to more powerful computing resources. Therefore, they can build harder algorithms that are more complex, which can still be used in production and benefit the person using it.
How Is Deep Learning Helpful?
Deep learning can work with complex textures. For instance, it’s not that hard if you have a simple object with a specific form. But if you have a space where the object is considered normal, for example, that could be some deviation for shape and texture.
So this is where deep learning comes in. Because it can, with a defined space of normality, it can alarm all the deviations from it. You can do more flexibility in the way we can use it.
Challenges Faced While Using Artificial Intelligence
One of the challenges is clearly defining what you want, like the space of normality. It’s also sometimes a very arguable process because it’s sometimes the decision if the quality is good or bad is based on the people’s experience, and you need to go through all their experiences and define what is good or bad, which can be a very interesting process.
Clear communication between the customer and the one creating the product helps overcome the challenges.
Artificial Intelligence is always a challenge. But to prove it, customers need to define some pilot where they can see all the possibilities that artificial intelligence could provide. It could be a very long pilot with a lot of testing to understand the capabilities of technology and how it can be used in production.
The company looks forward to improving its technology to make it faster, improve its quality, and find other industries/ factory processes where it could implement it.
