Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Probabilistic Circuits for Autonomous Learning: A Simulation Study.

ABSTRACT: Modern machine learning is based on powerful algorithms running on digital computing platforms and there is great interest in accelerating the learning process and making it more energy efficient. In this paper we present a fully autonomous probabilistic circuit for fast and efficient learning that makes no use of digital computing. Specifically we use SPICE simulations to demonstrate a clockless autonomous circuit where the required synaptic weights are read out in the form of analog voltages. This allows us to demonstrate a circuit that can be built with existing technology to emulate the Boltzmann machine learning algorithm based on gradient optimization of the maximum likelihood function. Such autonomous circuits could be particularly of interest as standalone learning devices in the context of mobile and edge computing.

SUBMITTER: Kaiser J

PROVIDER: S-EPMC7052495 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Probabilistic Circuits for Autonomous Learning: A Simulation Study.

Kaiser Jan J Faria Rafatul R Camsari Kerem Y KY Datta Supriyo S

Frontiers in computational neuroscience 20200225

Modern machine learning is based on powerful algorithms running on digital computing platforms and there is great interest in accelerating the learning process and making it more energy efficient. In this paper we present a fully autonomous probabilistic circuit for fast and efficient learning that makes no use of digital computing. Specifically we use SPICE simulations to demonstrate a clockless autonomous circuit where the required synaptic weights are read out in the form of analog voltages. ...[more]

PMID: 32161530

Similar Datasets

Learning probabilistic neural representations with randomly connected circuits.

Project description:The brain represents and reasons probabilistically about complex stimuli and motor actions using a noisy, spike-based neural code. A key building block for such neural computations, as well as the basis for supervised and unsupervised learning, is the ability to estimate the surprise or likelihood of incoming high-dimensional neural activity patterns. Despite progress in statistical modeling of neural responses and deep learning, current approaches either do not scale to large neural populations or cannot be implemented using biologically realistic mechanisms. Inspired by the sparse and random connectivity of real neuronal circuits, we present a model for neural codes that accurately estimates the likelihood of individual spiking patterns and has a straightforward, scalable, efficient, learnable, and realistic neural implementation. This model's performance on simultaneously recorded spiking activity of >100 neurons in the monkey visual and prefrontal cortices is comparable with or better than that of state-of-the-art models. Importantly, the model can be learned using a small number of samples and using a local learning rule that utilizes noise intrinsic to neural circuits. Slower, structural changes in random connectivity, consistent with rewiring and pruning processes, further improve the efficiency and sparseness of the resulting neural representations. Our results merge insights from neuroanatomy, machine learning, and theoretical neuroscience to suggest random sparse connectivity as a key design principle for neuronal computation.

| S-EPMC7547210 | biostudies-literature

Phasic Dopamine Changes and Hebbian Mechanisms during Probabilistic Reversal Learning in Striatal Circuits: A Computational Study.

Project description:Cognitive flexibility is essential to modify our behavior in a non-stationary environment and is often explored by reversal learning tasks. The basal ganglia (BG) dopaminergic system, under a top-down control of the pre-frontal cortex, is known to be involved in flexible action selection through reinforcement learning. However, how adaptive dopamine changes regulate this process and learning mechanisms for training the striatal synapses remain open questions. The current study uses a neurocomputational model of the BG, based on dopamine-dependent direct (Go) and indirect (NoGo) pathways, to investigate reinforcement learning in a probabilistic environment through a task that associates different stimuli to different actions. Here, we investigated: the efficacy of several versions of the Hebb rule, based on covariance between pre- and post-synaptic neurons, as well as the required control in phasic dopamine changes crucial to achieving a proper reversal learning. Furthermore, an original mechanism for modulating the phasic dopamine changes is proposed, assuming that the expected reward probability is coded by the activity of the winner Go neuron before a reward/punishment takes place. Simulations show that this original formulation for an automatic phasic dopamine control allows the achievement of a good flexible reversal even in difficult conditions. The current outcomes may contribute to understanding the mechanisms for active control of dopamine changes during flexible behavior. In perspective, it may be applied in neuropsychiatric or neurological disorders, such as Parkinson's or schizophrenia, in which reinforcement learning is impaired.

| S-EPMC8998230 | biostudies-literature

SLAV-Sim: A Framework for Self-Learning Autonomous Vehicle Simulation.

Project description:With the advent of autonomous vehicles, sensors and algorithm testing have become crucial parts of the autonomous vehicle development cycle. Having access to real-world sensors and vehicles is a dream for researchers and small-scale original equipment manufacturers (OEMs) due to the software and hardware development life-cycle duration and high costs. Therefore, simulator-based virtual testing has gained traction over the years as the preferred testing method due to its low cost, efficiency, and effectiveness in executing a wide range of testing scenarios. Companies like ANSYS and NVIDIA have come up with robust simulators, and open-source simulators such as CARLA have also populated the market. However, there is a lack of lightweight and simple simulators catering to specific test cases. In this paper, we introduce the SLAV-Sim, a lightweight simulator that specifically trains the behaviour of a self-learning autonomous vehicle. This simulator has been created using the Unity engine and provides an end-to-end virtual testing framework for different reinforcement learning (RL) algorithms in a variety of scenarios using camera sensors and raycasts.

| S-EPMC10611232 | biostudies-literature

Probabilistic switching circuits in DNA.

Project description:A natural feature of molecular systems is their inherent stochastic behavior. A fundamental challenge related to the programming of molecular information processing systems is to develop a circuit architecture that controls the stochastic states of individual molecular events. Here we present a systematic implementation of probabilistic switching circuits, using DNA strand displacement reactions. Exploiting the intrinsic stochasticity of molecular interactions, we developed a simple, unbiased DNA switch: An input signal strand binds to the switch and releases an output signal strand with probability one-half. Using this unbiased switch as a molecular building block, we designed DNA circuits that convert an input signal to an output signal with any desired probability. Further, this probability can be switched between 2 n different values by simply varying the presence or absence of n distinct DNA molecules. We demonstrated several DNA circuits that have multiple layers and feedback, including a circuit that converts an input strand to an output strand with eight different probabilities, controlled by the combination of three DNA molecules. These circuits combine the advantages of digital and analog computation: They allow a small number of distinct input molecules to control a diverse signal range of output molecules, while keeping the inputs robust to noise and the outputs at precise values. Moreover, arbitrarily complex circuit behaviors can be implemented with just a single type of molecular building block.

| S-EPMC5798357 | biostudies-literature

Learning probabilistic models of hydrogen bond stability from molecular dynamics simulation trajectories.

Project description:BackgroundHydrogen bonds (H-bonds) play a key role in both the formation and stabilization of protein structures. They form and break while a protein deforms, for instance during the transition from a non-functional to a functional state. The intrinsic strength of an individual H-bond has been studied from an energetic viewpoint, but energy alone may not be a very good predictor.MethodsThis paper describes inductive learning methods to train protein-independent probabilistic models of H-bond stability from molecular dynamics (MD) simulation trajectories of various proteins. The training data contains 32 input attributes (predictors) that describe an H-bond and its local environment in a conformation c and the output attribute is the probability that the H-bond will be present in an arbitrary conformation of this protein achievable from c within a time duration Δ. We model dependence of the output variable on the predictors by a regression tree.ResultsSeveral models are built using 6 MD simulation trajectories containing over 4000 distinct H-bonds (millions of occurrences). Experimental results demonstrate that such models can predict H-bond stability quite well. They perform roughly 20% better than models based on H-bond energy alone. In addition, they can accurately identify a large fraction of the least stable H-bonds in a conformation. In most tests, about 80% of the 10% H-bonds predicted as the least stable are actually among the 10% truly least stable. The important attributes identified during the tree construction are consistent with previous findings.ConclusionsWe use inductive learning methods to build protein-independent probabilistic models to study H-bond stability, and demonstrate that the models perform better than H-bond energy alone.

| S-EPMC3044290 | biostudies-literature

Using simulation to accelerate autonomous experimentation: A case study using mechanics.

Project description:Autonomous experimentation (AE) accelerates research by combining automation and machine learning to perform experiments intelligently and rapidly in a sequential fashion. While AE systems are most needed to study properties that cannot be predicted analytically or computationally, even imperfect predictions can in principle be useful. Here, we investigate whether imperfect data from simulation can accelerate AE using a case study on the mechanics of additively manufactured structures. Initially, we study resilience, a property that is well-predicted by finite element analysis (FEA), and find that FEA can be used to build a Bayesian prior and experimental data can be integrated using discrepancy modeling to reduce the number of needed experiments ten-fold. Next, we study toughness, a property not well-predicted by FEA and find that FEA can still improve learning by transforming experimental data and guiding experiment selection. These results highlight multiple ways that simulation can improve AE through transfer learning.

| S-EPMC8010472 | biostudies-literature

Autonomous microfluidic capillaric circuits replicated from 3D-printed molds.

Project description:We recently developed capillaric circuits (CCs) - advanced capillary microfluidic devices assembled from capillary fluidic elements in a modular manner similar to the design of electric circuits (Safavieh & Juncker, Lab Chip, 2013, 13, 4180-4189). CCs choreograph liquid delivery operations according to pre-programmed capillary pressure differences with minimal user intervention. CCs were thought to require high-precision micron-scale features manufactured by conventional photolithography, which is slow and expensive. Here we present CCs manufactured rapidly and inexpensively using 3D-printed molds. Molds for CCs were fabricated with a benchtop 3D-printer, poly(dimethylsiloxane) replicas were made, and fluidic functionality was verified with aqueous solutions. We established design rules for CCs by a combination of modelling and experimentation. The functionality and reliability of trigger valves - an essential fluidic element that stops one liquid until flow is triggered by a second liquid - was tested for different geometries and different solutions. Trigger valves with geometries up to 80-fold larger than cleanroom-fabricated ones were found to function reliably. We designed retention burst valves that encode sequential liquid delivery using capillary pressure differences encoded by systematically varied heights and widths. Using an electrical circuit analogue of the CC, we established design rules to ensure strictly sequential liquid delivery. CCs autonomously delivered eight liquids in a pre-determined sequence in <7 min. Taken together, our results demonstrate that 3D-printing lowers the bar for other researchers to access capillary microfluidic valves and CCs for autonomous liquid delivery with applications in diagnostics, research and education.

| S-EPMC5314688 | biostudies-literature

Combining temporal planning with probabilistic reasoning for autonomous surveillance missions.

Project description:It is particularly challenging to devise techniques for underpinning the behaviour of autonomous vehicles in surveillance missions as these vehicles operate in uncertain and unpredictable environments where they must cope with little stability and tight deadlines in spite of their restricted resources. State-of-the-art techniques typically use probabilistic algorithms that suffer a high computational cost in complex real-world scenarios. To overcome these limitations, we propose a hybrid approach that combines the probabilistic reasoning based on the target motion model offered by Monte Carlo simulation with long-term strategic capabilities provided by automated task planning. We demonstrate our approach by focusing on one particular surveillance mission, search-and-tracking, and by using two different vehicles, a fixed-wing UAV deployed in simulation and the "Parrot AR.Drone2.0" quadcopter deployed in a physical environment. Our experimental results show that our unique way of integrating probabilistic and deterministic reasoning pays off when we tackle realistic missions.

| S-EPMC7175604 | biostudies-literature