James Y. S. Tan | Searcharxiv

arXiv2024

Foundry's perspective on laser and SOA module integration with silicon photonics

Silicon photonic integrated circuit (PIC) builds on the demand for a low cost approach from established silicon-based manufacturing infrastructure traditionally built for electronics. Besides its natural abundance, silicon has desirable properties such as optically low loss (at certain critical wavelengths), and small form factor to enable high density scaled-up optical on-chip circuitry. However, given its indirect bandgap, the platform is typically integrated with other direct bandgap (e.g., III-V semiconductor) platforms for on-chip light source. An effective solution to integrating light source onto silicon photonics platform is integral to a practical scaled-up and full-fledged integrated photonics implementation. Here, we discuss the integration solutions, and present our foundry's perspective toward realizing it.

physics.app-ph↗

arXiv2022

Monadic Pavlovian associative learning in a backpropagation-free photonic network

Over a century ago, Ivan P. Pavlov, in a classic experiment, demonstrated how dogs can learn to associate a ringing bell with food, thereby causing a ring to result in salivation. Today, it is rare to find the use of Pavlovian type associative learning for artificial intelligence (AI) applications even though other learning concepts, in particular backpropagation on artificial neural networks (ANNs) have flourished. However, training using the backpropagation method on 'conventional' ANNs, especially in the form of modern deep neural networks (DNNs), is computationally and energy intensive. Here we experimentally demonstrate a form of backpropagation-free learning using a single (or monadic) associative hardware element. We realize this on an integrated photonic platform using phase-change materials combined with on-chip cascaded directional couplers. We then develop a scaled-up circuit network using our monadic Pavlovian photonic hardware that delivers a distinct machine-learning framework based on single-element associations and, importantly, using backpropagation-free architectures to address general learning tasks. Our approach reduces the computational burden imposed by learning in conventional neural network approaches, thereby increasing speed, whilst also offering higher bandwidth inherent to our photonic implementation.

physics.optics↗