Dataset Information

Trainable hardware for dynamical computing using error backpropagation through physical media.

ABSTRACT: Neural networks are currently implemented on digital Von Neumann machines, which do not fully leverage their intrinsic parallelism. We demonstrate how to use a novel class of reconfigurable dynamical systems for analogue information processing, mitigating this problem. Our generic hardware platform for dynamic, analogue computing consists of a reciprocal linear dynamical system with nonlinear feedback. Thanks to reciprocity, a ubiquitous property of many physical phenomena like the propagation of light and sound, the error backpropagation-a crucial step for tuning such systems towards a specific task-can happen in hardware. This can potentially speed up the optimization process significantly, offering important benefits for the scalability of neuro-inspired hardware. In this paper, we show, using one experimentally validated and one conceptual example, that such systems may provide a straightforward mechanism for constructing highly scalable, fully dynamical analogue computers.

SUBMITTER: Hermans M

PROVIDER: S-EPMC4382991 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Biological Regulatory Networks (BRNs) are responsible for developmental and maintenance related functions in organisms. These functions are implemented by the dynamics of BRNs and are sensitive to regulations enforced by specific activators and inhibitors. The logical modeling formalism by René Thomas incorporates this sensitivity with a set of logical parameters modulated by available regulators, varying with time. With the increase in complexity of BRNs in terms of number of entities and their interactions, the task of parameters estimation becomes computationally expensive with existing sequential SMBioNET tool. We extend the existing sequential implementation of SMBioNET by using a data decomposition approach using a Java messaging library called MPJ Express. The approach divides the parameters space into different regions and each region is then explored in parallel on High Performance Computing (HPC) hardware. RESULTS:The performance of the parallel approach is evaluated on BRNs of different sizes, and experimental results on multicore and cluster computers showed almost linear speed-up. This parallel code can be executed on a wide range of concurrent hardware including laptops equipped with multicore processors, and specialized distributed memory computer systems. To demonstrate the application of parallel implementation, we selected a case study of Hexosamine Biosynthetic Pathway (HBP) in cancer progression to identify potential therapeutic targets against cancer. A set of logical parameters were computed for HBP model that directs the biological system to a state of recovery. Furthermore, the parameters also suggest a potential therapeutic intervention that restores homeostasis. Additionally, the performance of parallel application was also evaluated on a network (comprising of 23 entities) of Fibroblast Growth Factor Signalling in Drosophila melanogaster. CONCLUSIONS:Qualitative modeling framework is widely used for investigating dynamics of biological regulatory networks. However, computation of model parameters in qualitative modeling is computationally intensive. In this work, we presented results of our Java based parallel implementation that provides almost linear speed-up on both multicore and cluster platforms. The parallel implementation is available at https://psmbionet.github.io .

Dataset Information

Trainable hardware for dynamical computing using error backpropagation through physical media.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure