Abstract: Apparatuses, systems, and techniques to identify out-of-distribution input data in one or more neural networks. In at least one embodiment, a technique includes training one or more neural networks to infer a plurality of characteristics about input information based, at least in part, on the one or more neural networks being independently trained to infer each of the plurality of characteristics about the input information.

Abstract: As one example, an apparatus includes a dielectric microsensor having a microfluidic chamber that includes a capacitive sensing structure. The microfluidic chamber is adapted to receive a volume of a blood sample, and a bioactive agent is adapted to interact with the blood sample, as a sample under test (SUT), within the microfluidic chamber. A transmitter can provide an input radio frequency (RF) signal to the dielectric microsensor, and a receiver can receive an output RF signal from the dielectric microsensor. A computing device is configured to compute dielectric permittivity values for the SUT based on the output RF signal over a time interval in which the dielectric permittivity values are representative of the bioactive agent interacting with the blood sample over the time interval. The computing device is further configured to provide a readout representative of hemostatic dysfunction for the blood sample based on the dielectric permittivity values.

Abstract: Apparatuses, systems, and techniques to identify out-of-distribution input data in one or more neural networks. In at least one embodiment, a technique includes training one or more neural networks to infer a plurality of characteristics about input information based, at least in part, on the one or more neural networks being independently trained to infer each of the plurality of characteristics about the input information.

Abstract: Apparatuses, systems, and techniques to identify out-of-distribution input data in one or more neural networks. In at least one embodiment, a technique includes training a first portion of a neural network in a first set of data, and training a second portion of the neural network on a second set of data, where the first and second sets of data are similar within a first range.