As artificial intelligence becomes more advanced, previously cutting-edge — but generic — AI models are becoming commonplace, such as Google Cloud’s or .
While effective in some use cases, these solutions do not suit industry-specific needs immediately. Organizations seeking the most accurate results from their AI projects must turn to industry-specific models.
Anyits AI capabilities should apply its data and use cases to a generic model and assess the results.
There are a few ways that. One would be to adopt a hybrid approach — taking an open-source generic AI model and training it further to align with the business’s . Companies could also look to third-party vendors, such as IBM or C3, and access a complete solution right off the shelf. Or — if they needed to — data science their models in-house, from scratch.
Let’s dive into these approaches and howfor their distinct circumstances.
Generic models alone often don’t cut it.
Generic AI models like Vision AI or Rekognition and open-source ones from TensorFlow or Scikit-learn often fail to produce satisfactory results for niche use cases in finance or the energy sector. Many businesses have unique needs, and models that don’t have the contextualindustry will not be able to provide relevant results.
Building on top of open-source models
At ThirdEye Data, we recently worked with a utility company to tag and detect defects in electric poles by using AI to analyze thousands of images. We started using Google Vision API and found that it could not produce our desired results — with the precision and recall values of the AI models completely unusable. The models could not read the characters within the tags on the electric poles 90% of thethe nonstandard font and varying background colors used in the titles. So, we took base models from TensorFlow and optimized them to the utility company’s precise needs. After two months of and decipher tags on the electric poles and another two months of training these models, the results display accuracy levels of over 90%.
These will continue towith retraining iterations. Any team looking to expand its AI capabilities should apply its data and use cases to a generic the results. Then, if the results are insufficient, the team can extend the algorithm by training it further on their industry-specific data. Companies can start with open-source algorithms on AI and ML frameworks like TensorFlow, Scikit-learn, or . At ThirdEye Data, we used convolutional neural network (CNN) algorithms on TensorFlow.