Search

Classification and recognition tasks performed on photonic hardware-based neural networks often require at least one offline computational step, such as in the increasingly popular reservoir computing paradigm. Removing this offline step can significantly improve the response time and energy efficiency of such systems. We present numerical simulations of different algorithms that utilize ultrafast photonic spiking neurons as receptive fields to allow for image recognition without an offline computing step. In particular, we discuss the merits of event, spike-time and rank-order based algorithms adapted to this system. These techniques have the potential to significantly improve the efficiency and effectiveness of optical classification systems, minimizing the number of spiking nodes required for a given task and leveraging the parallelism offered by photonic hardware.

Recently, a Cambrian explosion of a novel, non-volatile memory (NVM) devices known as memristive devices have inspired effort in building hardware neural networks that learn like the brain. Early experimental prototypes built simple perceptrons from nanosynapses, and recently, fully-connected multi-layer perceptron (MLP) learning systems have been realized. However, while backpropagating learning systems pair well with high-precision computer memories and achieve state-of-the-art performances, this typically comes with a massive energy budget. For future Internet of Things/peripheral use cases, system energy footprint will be a major constraint, and emerging NVM devices may fill the gap by sacrificing high bit precision for lower energy. In this paper, we contrast the well-known MLP approach with the extreme learning machine (ELM) or NoProp approach, which uses a large layer of random weights to improve the separability of high-dimensional tasks, and is usually considered inferior in a software context. However, we find that when taking the device non-linearity into account, NoProp manages to equal hardware MLP system in terms of accuracy. While also using a sign-based adaptation of the delta rule for energy-savings, we find that NoProp can learn effectively with four to six 'bits' of device analog capacity, while MLP requires eight-bit capacity with the same rule. This may allow the requirements for memristive devices to be relaxed in the context of online learning. By comparing the energy footprint of these systems for several candidate nanosynapses and realistic peripherals, we confirm that memristive NoProp systems save energy compared with MLP systems. Lastly, we show that ELM/NoProp systems can achieve better generalization abilities than nanosynaptic MLP systems when paired with pre-processing layers (which do not require backpropagated error). Collectively, these advantages make such systems worthy of consideration in future accelerators or embedded hardware.

In the past two decades, research into the biochemical, biophysical and structural properties of the ribosome have revealed many different steps of protein translation. Nevertheless, a complete understanding of how they lead to a rapid and accurate protein synthesis still remains a challenge. Here we consider a coarse network analysis in the bacterial ribosome formed by the connectivity between ribosomal (r) proteins and RNAs at different stages in the elongation cycle. The ribosomal networks are found to be dis-assortative and small world, implying that the structure allows for an efficient exchange of information between distant locations. An analysis of centrality shows that the second and fifth domains of 23S rRNA are the most important elements in all of the networks. Ribosomal protein hubs connect to much fewer nodes but are shown to provide important connectivity within the network (high closeness centrality). A modularity analysis reveals some of the different functional communities, indicating some known and some new possible communication pathways Our mathematical results confirm important communication pathways that have been discussed in previous research, thus verifying the use of this technique for representing the ribosome, and also reveal new insights into the collective function of ribosomal elements.