I began my DNN career path researching cancerous tissue detection for medical diagnostic imaging which is a computer vision problem. I think it would surprise a lot of people how power efficient you can make DNNs (especially for inference) when it comes to other tasks besides predicting text or generating media. It pleases me greatly to see other peers in my field share my prognosis about language models compared to other DNN algorithms for different modalities.
Thanks for your input, reassurance, and well done in helping to create such an efficient system.
Maybe this helps for people stumbling over this thread: A Google Coral device can do classification on images with around 18fps. That is a 2w USB device.
That is the power of a well built DNN.
And you can adapt this this stuff like Monitoring data, network traffic and much more. All “AI”, same basic technology like ChatGPT and Claude but made for specific tasks. And they do their tasks damn fucking well
I began my DNN career path researching cancerous tissue detection for medical diagnostic imaging which is a computer vision problem. I think it would surprise a lot of people how power efficient you can make DNNs (especially for inference) when it comes to other tasks besides predicting text or generating media. It pleases me greatly to see other peers in my field share my prognosis about language models compared to other DNN algorithms for different modalities.
Thanks for your input, reassurance, and well done in helping to create such an efficient system.
Maybe this helps for people stumbling over this thread: A Google Coral device can do classification on images with around 18fps. That is a 2w USB device.
That is the power of a well built DNN.
And you can adapt this this stuff like Monitoring data, network traffic and much more. All “AI”, same basic technology like ChatGPT and Claude but made for specific tasks. And they do their tasks damn fucking well