Opportunities for neuromorphic computing algorithms and applications.

Neuromorphic computing technologies will be important for the future of computing, but much of the work in neuromorphic computing has focused on hardware development. Here, we review recent results in neuromorphic computing algorithms and applications. We highlight characteristics of neuromorphic computing technologies that make them attractive for the future of computing and we discuss opportunities for future development of algorithms and applications on these systems.

Spiking neural networks for handwritten digit recognition-Supervised learning and network optimization.

We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications.

What's in a number? Recommending practicality in the DATA 2000 patient limits.

According to the Substance Abuse and Mental Health Services Administration, 2.4 million individuals have an opioid use disorder (OUD). Yet, nearly 80 percent of them-more than 1.9 million people-do not receive treatment. Medication-assisted treatment (MAT), specifically with buprenorphine, has proven to be effective in treating patients with OUDs while also reducing costs to the healthcare system, criminal justice system, and workforce. Despite its effectiveness, barriers to MAT continue to exist. Consequently, many individuals must wait months, if not years, to receive treatment. This article analyzes the US Department of Health and Human Services' final rule (Final Rule) on MAT, common barriers to treatment, and the cost-benefit of treatment in light of the current opioid abuse epidemic. The article finds that while the Final Rule was a step in the right direction, it does not go far enough to adequately address the epidemic. Finally, the article proposes practical recommendations for increasing patient access to treatment for OUDs, including increasing the patient limit for highly qualified addiction treatment providers so that they can practice addiction medicine on a full-time basis and exempting buprenorphine products labeled by the US Food and Drug Administration for direct administration from the practitioner's patient limit.