arXiv subjects
Publications and source records attributed to Erfan Khoram.
Metasurfaces have been used to realize optical functions such as focusing and beam steering. They use sub-wavelength nanostructures to control the local amplitude and phase of light. Here we show that such control could also enable a new function of artificial neural inference. We demonstrate that metasurfaces can directly recognize objects by focusing light from an object to different spatial locations that correspond to the class of the object.
Adjoint optimization is an effective method in the inverse design of nanophotonic devices. In order to ensure the manufacturability, one would like to have control over the minimal feature sizes. Here we propose utilizing a level-set method based on b-spline surfaces in order to control the feature sizes. This approach is first used to design a wavelength demultiplexer. It is also used to implement a nanophotonic structure for artificial neural computing. In both cases, we show that the minimal feature sizes can be easily parameterized and controlled.
We show optical waves passing through a nanophotonic medium can perform artificial neural computing. Complex information, is encoded in the wave front of an input light. The medium transforms the wave front to realize sophisticated computing tasks such as image recognition. At the output, the optical energy is concentrated to well-defined locations, which for example can be interpreted as the identity of the object in the image. These computing media can be as small as tens of wavelengths and offer ultra-high computing density. They exploit sub-wavelength scatterers to realize complex input output mapping beyond the capabilities of traditional nanophotonic devices.
A complete system solution extracting signals from the patient chest with three leads including motion artifact removal in both analog and digital implementations are described. The resulting ECG signal is transferred via Bluetooth low energy to a mobile phone. Using deep sleep modes, the overall power consumption is less than 300 $μ$A and the device can operate for more than 20 days using a 150mAh battery. The screening software looks for suspicious traces such as those with missing pulses, tachycardia, bradycardia, etc. The mobile phone software also eliminates any remaining motion artifact. The traces are subsequently processed in detail in a cloud server and to a physicians dashboard for long-term monitoring.
Data inconsistency leads to a slow training process when deep neural networks are used for the inverse design of photonic devices, an issue that arises from the fundamental property of non-uniqueness in all inverse scattering problems. Here we show that by combining forward modeling and inverse design in a tandem architecture, one can overcome this fundamental issue, allowing deep neural networks to be effectively trained by data sets that contain non-unique electromagnetic scattering instances. This paves the way for using deep neural networks to design complex photonic structures that requires large training sets.