An official website of the United States government
Deep learning accomplishes remarkable success through training with massively labeled datasets. However, the high demands on the datasets impede the feasibility of deep learning in edge computing scenarios and suffer the data scarcity issue. Rather than relying on labeled data, animals learn by interacting with their surroundings and memorizing the relationship between concurrent events. This learning paradigm is referred to as associative memory. The successful implementation of associative memory potentially achieves self-learning schemes analogous to animals to resolve the challenges of deep learning. The state-of-the-art implementations of associative memory are limited to small-scale and offline paradigms. Thus, in this work, we implement associative memory learning with an Unmanned Ground Vehicle (UGV) and neuromorphic chips (Intel Loihi) for an online learning scenario. Our system reproduces the classic associative memory in rats. In specific, our system successfully reproduces the fear conditioning with no pretraining procedure and labeled datasets. In our experiments, the UGV serves as a substitute for the rats. Our UGV autonomously memorizes the cause-and-effect of the light stimulus and vibration stimulus, then exhibits a movement response. During associative memory learning, the synaptic weights are updated by Hebbian learning. The Intel Loihi chip is integrated with our online learning system for processing visual signals. Its average power usages for computing logic and memory are 30 mW and 29 mW, respectively.
more »
« less
Implementation of Associative Memory Learning in Mobile Robots Using Neuromorphic Computing
Fear conditioning is a behavioral paradigm of learning to predict aversive events. It is a form of associative learning that memorizes an undesirable stimulus (e.g., an electrical shock) and a neutral stimulus (e.g., a tone), resulting in a fear response (such as running away) to the originally neutral stimulus. The association of concurrent events is implemented by strengthening the synaptic connection between the neurons. In this paper, with an analogous methodology, we reproduce the classic fear conditioning experiment of rats using mobile robots and a neuromorphic system. In our design, the acceleration from a vibration platform substitutes the undesirable stimulus in rats. Meanwhile, the brightness of light (dark vs. light) is used for a neutral stimulus, which is analogous to the neutral sound in fear conditioning experiments in rats. The brightness of the light is processed with sparse coding in the Intel Loihi chip. The simulation and experimental results demonstrate that our neuromorphic robot successfully, for the first time, reproduces the fear conditioning experiment of rats with a mobile robot. The work exhibits a potential online learning paradigm with no labeled data required. The mobile robot directly memorizes the events by interacting with its surroundings, essentially different from data-driven methods.
more »
« less
- Award ID(s):
- 2245712
- PAR ID:
- 10516665
- Publisher / Repository:
- Intech Open
- Date Published:
- Journal Name:
- Neuromorphic Computing
- ISSN:
- 2633-1403
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Social transmission of fear occurs in a subset of individuals, where an Observer displays a fear response to a previously neutral stimulus after witnessing or interacting with a conspecific Demonstrator during memory retrieval. The conditions under which fear can be acquired socially in rats have received attention in recent years, and suggest that social factors modulate social transmission of information. We previously found that one such factor, social rank, impacts fear conditioning by proxy in male rats. Here, we aimed to investigate whether social roles as determined by nape contacts in females, might also have an influence on social transmission of fear. In-line with previous findings in males, we found that social interactions in the home cage can provide insight into the social relationship between female rats and that these relationships predict the degree of fear acquired by-proxy. These results suggest that play behavior affects the social transfer/transmission of information in female rats.more » « less
-
Contexts and discrete stimuli often hierarchically influence the association between a stimulus and outcome. This phenomenon, called occasion setting, is central to modulation-based Pavlovian learning. We conducted two experiments with humans in fear and appetitive conditioning paradigms, training stimuli in differential conditioning, feature-positive discriminations, and feature-negative discriminations. We also investigated the effects of trait anxiety and trait depression on these forms of learning. Results from both experiments showed that participants were able to successfully learn which stimuli predicted the electric shock and monetary reward outcomes. Additionally, as hypothesized, the stimuli trained as occasion setters had little-to-no effect on simple reinforced or non-reinforced stimuli, suggesting the former were indeed occasion setters. Lastly, in fear conditioning, trait anxiety was associated with increases in fear of occasion setter/conditional stimulus compounds; in appetitive conditioning, trait depression was associated with lower expectations of monetary reward for the trained negative occasion setting compound and transfer of the negative occasion setter to the simple reinforced stimulus. These results suggest that clinically anxious individuals may have enhanced fear of occasion setting compounds, and clinically depressed individuals may expect less reward with compounds involving the negative occasion setter.more » « less
-
Deep neural networks (DNNs) have achieved remarkable success in various cognitive tasks through training on extensive labeled datasets. However, the heavy reliance on these datasets poses challenges for DNNs in scenarios with energy constraints in particular scenarios, such as on the moon. On the contrary, animals exhibit a self-learning capability by interacting with their surroundings and memorizing concurrent events without annotated data—a process known as associative learning. A classic example of associative learning is when a rat memorizes desired and undesired stimuli while exploring a T-maze. The successful implementation of associative learning aims to replicate the self-learning mechanisms observed in animals, addressing challenges in data-constrained environments. While current implementations of associative learning are predominantly small scale and offline, this work pioneers associative learning in a robot equipped with a neuromorphic chip, specifically for online learning in a T-maze. The system successfully replicates classic associative learning observed in rodents, using neuromorphic robots as substitutes for rodents. The neuromorphic robot autonomously learns the cause-and-effect relationship between audio and visual stimuli.more » « less
-
Generalization allows previous experience to adaptively guide behavior when conditions change. The infralimbic (IL) subregion of the ventromedial prefrontal cortex plays a known role in generalization processes, although mechanisms remain unclear. A basic physical unit of memory storage and expression in the brain is a sparse, distributed group of neurons known as an engram. Here, we set out to determine whether an engram established during learning contributes to generalized responses in IL. Generalization was tested in male and female mice by presenting a novel, ambiguous, tone generalization stimulus following pavlovian defensive (fear) conditioning. The first experiment was designed to test a global role for IL in generalization using chemogenetic manipulations. Results show IL regulates defensive behavior in response to ambiguous stimuli. IL silencing led to a switch in defensive state, from vigilant scanning to generalized freezing, while IL stimulation reduced freezing in favor of scanning. Leveraging activity-dependent “tagging” technology (ArcCreERT2 × eYFP system), an engram, preferentially located in IL Layer 2/3, was associated with the generalization stimulus. Remarkably, in the identical discrete location, fewer reactivated neurons were associated with the generalization stimulus at the remote timepoint (30 d) following learning. When an IL engram established during learning was selectively chemogenetically silenced, freezing increased. Conversely, IL engram stimulation reduced freezing, suggesting attenuated fear generalization. Overall, these data identify a crucial role for IL in suppressing generalized conditioned responses. Further, an IL engram formed during learning functions to later attenuate a conditioned response in the presence of ambiguous threat stimuli.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.5772/intechopen.110364
