From Quadrant (a D-Wave business), this whitepaper “Data-Efficient Machine Learning” describes a practical impediment to the application of deep neural network models when large training data sets are unavailable. Encouragingly however, it is shown that recent machine learning advances make it possible to obtain the benefits of deep neural networks by making more efficient use of training data that most practitioners do have.
Quadrant leverages generative machine learning, which requires much less labeled data than common discriminative models. This is incredibly useful in countless applications, including medical imaging which is often limited to relatively small data sets (i.e. 50 videos of cataract surgery or a discrete set of brain scans from deceased patients). For a first case study, Siemens Healthineers partnered with Quadrant to identify surgical tools used in cataract surgery with 99.71% accuracy. Annotating tool usage enables surgical workflow analysis, which in turn improves surgical training and even real-time decision support.
Right now, Quadrant is running on GPUs because D-Wave wanted more companies to have access to the algorithms, but the models are “quantum ready” meaning they are equipped to run on D-Wave’s forthcoming next-gen quantum processor. Download the whitepaper HERE.
Sign up for the free insideBIGDATA newsletter.
Speak Your Mind