Issue link: https://iconnect007.uberflip.com/i/1166358
SEPTEMBER 2019 I PCB007 MAGAZINE 43 for testing to be in accordance with IPC-9252. However, certified test for military products must state the applicable performance specifi- cation used to be recorded for annual reporting and information retention. PCB007 Todd Kolmodin is VP of quality for Gardien Services USA and an expert in electrical test and reliability issues. To read past columns or contact Kolmodin, click here. Conclusion Overall, you must read the fine print when viewing specifications and drawings. Just be- cause the master drawing states an IPC general build specification does not mean an ET C of C will state that specification. Most IPC specifi- cation call for IPC-9252 as the ET specification, and it is correct that the ET C of C state IPC- 9252 revision, class, and test level. The only exception is for aerospace and military avion- ics special requirements. It is also not uncom- mon to see the IPC-9252 specification on an ET C of C along with an applicable military speci- fication. Many military specifications also call each individual network of this set is specialized to spe- cifically recognize a sub-group of object classes. According to SPIE Fellow Aydogan Ozcan of the Uni- versity of California, Los Angeles, and one of the paper's authors, these results "provide a major advancement to bring optical neural network-based low-power and low- latency solutions for various machine-learning applica- tions." This latest research is a significant advance to Ozcan's optical machine-learning framework. The finessing of this technology is especially significant for recognizing target objects more quickly and with significantly less power than standard computer-based machine learning systems. Ultimately, it may provide major advantages for autonomous ve- hicles, robotics, and various defense-related applications, among others. These latest systematic advances in dif- fractive optical network designs, in particular, have the potential to advance the develop- ment of next-generation, task-specific, and in- telligent computational camera systems. The article authors are Jingxi Li, Deniz Mengu, Yi Luo, Yair Rivenson, and Aydogan Ozcan of the University of California at Los Angeles Depart- ment of Electrical and Computer Engineering and California NanoSystems Institute in Los Angeles, California, USA. (Source: SPIE) A new paper in Advanced Photonics, an open-access journal co-published by SPIE, the international society for optics and photonics, and Chinese Laser Press (CLP), demonstrates distinct improvements to the inference and generalization performance of diffractive optical neural networks. One of the key improvements discussed in the paper, "Class-specific differential detection in diffractive optical neural networks improves inference accuracy," incorpo- rates a differential detection scheme combined with a set of parallel-operating diffractive optical networks where All-optical Diffractive Neural Network Closes Performance Gap With Electronic Neural Networks