scholarly journals Human learning follows the dynamics of gradient descent

2021 ◽  
Author(s):  
Daniel N Barry ◽  
Bradley C. Love
Keyword(s):  
Neural Networks ◽  
Gradient Descent ◽  
Hidden Markov ◽  
Mental Representations ◽  
Strong Predictor ◽  
Significant Proportion ◽  
Human Learning ◽  
Markov Modelling ◽  
Human Participants ◽  
Level Performance

Artificial neural networks (ANNs) have achieved near human-level performance on many tasks and can account for human behavioural and brain measures in a number of domains. Although a principal strength of ANNs is learning representations from experience, only a handful of contributions have evaluated this process to ask whether ANN learning dynamics provide a good model of human learning. We investigated whether humans learn similarly to an ANN, which adjusts its representations through gradient descent. Gradient descent learning is steep at first and initially ignores covariance between features. ANNs can theoretically display a non-monotonic behaviour in which early in learning, multiple weak predictors determine the ANN’s decision whereas late in learning a single strong predictor can dominate. This initial behaviour was confirmed in a simple ANN and in half of human participants performing a comparable task. Later in gradient descent learning, the ANN changed to placing a greater weight on the stronger predictor, and humans also shifted their preferences in the same way. Hidden Markov modelling of the behaviour of ANNs and humans predicted similar transitions from weak-feature to strong-feature states. Our results suggest a significant proportion of people learn about categories in a manner analogous to ANNs, possibly by updating their mental representations by a process akin to gradient descent. Our findings demonstrate how ANNs can be used to not only explain the products of human learning but also the process.

scholarly journals Human learning follows the dynamics of gradient descent

2021 ◽  
Author(s):  
Daniel N Barry ◽  
Bradley C. Love
Keyword(s):  
Neural Networks ◽  
Gradient Descent ◽  
Hidden Markov ◽  
Mental Representations ◽  
Strong Predictor ◽  
Significant Proportion ◽  
Human Learning ◽  
Markov Modelling ◽  
Human Participants ◽  
Level Performance

Artificial neural networks (ANNs) have achieved near human-level performance on many tasks and can account for human behavioural and brain measures in a number of domains. Although a principal strength of ANNs is learning representations from experience, only a handful of contributions have evaluated this process to ask whether ANN learning dynamics provide a good model of human learning. We investigated whether humans learn similarly to an ANN, which adjusts its representations through gradient descent. Gradient descent learning is steep at first and initially ignores covariance between features. ANNs can theoretically display a non-monotonic behaviour in which early in learning, multiple weak predictors determine the ANN’s decision whereas late in learning a single strong predictor can dominate. This initial behaviour was confirmed in a simple ANN and in half of human participants performing a comparable task. Later in gradient descent learning, the ANN changed to placing a greater weight on the stronger predictor, and humans also shifted their preferences in the same way. Hidden Markov modelling of the behaviour of ANNs and humans predicted similar transitions from weak-feature to strong-feature states. Our results suggest a significant proportion of people learn about categories in a manner analogous to ANNs, possibly by updating their mental representations by a process akin to gradient descent. Our findings demonstrate how ANNs can be used to not only explain the products of human learning but also the process.

scholarly journals Synthetic neural-like computing in microbial consortia for pattern recognition

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Ximing Li ◽  
Luna Rizik ◽  
Valeriia Kravchik ◽  
Maria Khoury ◽  
Netanel Korin ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Gradient Descent ◽  
Biological Systems ◽  
Logic Gates ◽  
Structural Similarity ◽  
Microbial Consortia ◽  
Promoter Strength ◽  
Chemical Inducers ◽  
Artificial Neural

AbstractComplex biological systems in nature comprise cells that act collectively to solve sophisticated tasks. Synthetic biological systems, in contrast, are designed for specific tasks, following computational principles including logic gates and analog design. Yet such approaches cannot be easily adapted for multiple tasks in biological contexts. Alternatively, artificial neural networks, comprised of flexible interactions for computation, support adaptive designs and are adopted for diverse applications. Here, motivated by the structural similarity between artificial neural networks and cellular networks, we implement neural-like computing in bacteria consortia for recognizing patterns. Specifically, receiver bacteria collectively interact with sender bacteria for decision-making through quorum sensing. Input patterns formed by chemical inducers activate senders to produce signaling molecules at varying levels. These levels, which act as weights, are programmed by tuning the sender promoter strength Furthermore, a gradient descent based algorithm that enables weights optimization was developed. Weights were experimentally examined for recognizing 3 × 3-bit pattern.

scholarly journals Exploring Optimized Spiking Neural Network Architectures for Classification Tasks on Embedded Platforms

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3240
Author(s):  
Tehreem Syed ◽  
Vijay Kakani ◽  
Xuenan Cui ◽  
Hakil Kim
Keyword(s):  
Neural Networks ◽  
Gradient Descent ◽  
Spiking Neural Networks ◽  
License Plate ◽  
Training Techniques ◽  
Neuromorphic Hardware ◽  
Private And Public ◽  
Embedded Platforms ◽  
Public Datasets ◽  
Event Based

In recent times, the usage of modern neuromorphic hardware for brain-inspired SNNs has grown exponentially. In the context of sparse input data, they are undertaking low power consumption for event-based neuromorphic hardware, specifically in the deeper layers. However, using deep ANNs for training spiking models is still considered as a tedious task. Until recently, various ANN to SNN conversion methods in the literature have been proposed to train deep SNN models. Nevertheless, these methods require hundreds to thousands of time-steps for training and still cannot attain good SNN performance. This work proposes a customized model (VGG, ResNet) architecture to train deep convolutional spiking neural networks. In this current study, the training is carried out using deep convolutional spiking neural networks with surrogate gradient descent backpropagation in a customized layer architecture similar to deep artificial neural networks. Moreover, this work also proposes fewer time-steps for training SNNs with surrogate gradient descent. During the training with surrogate gradient descent backpropagation, overfitting problems have been encountered. To overcome these problems, this work refines the SNN based dropout technique with surrogate gradient descent. The proposed customized SNN models achieve good classification results on both private and public datasets. In this work, several experiments have been carried out on an embedded platform (NVIDIA JETSON TX2 board), where the deployment of customized SNN models has been extensively conducted. Performance validations have been carried out in terms of processing time and inference accuracy between PC and embedded platforms, showing that the proposed customized models and training techniques are feasible for achieving a better performance on various datasets such as CIFAR-10, MNIST, SVHN, and private KITTI and Korean License plate dataset.

Understanding Memories of the Past in the Context of Different Complex Neural Network Architectures

2022 ◽  
pp. 1-27
Author(s):  
Clifford Bohm ◽  
Douglas Kirkpatrick ◽  
Arend Hintze
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Mental Representations ◽  
Network Architectures ◽  
Information Theoretic ◽  
Time Points ◽  
The Past ◽  
Black Boxes ◽  
Past Experiences ◽  
Computational Systems

Abstract Deep learning (primarily using backpropagation) and neuroevolution are the preeminent methods of optimizing artificial neural networks. However, they often create black boxes that are as hard to understand as the natural brains they seek to mimic. Previous work has identified an information-theoretic tool, referred to as R, which allows us to quantify and identify mental representations in artificial cognitive systems. The use of such measures has allowed us to make previous black boxes more transparent. Here we extend R to not only identify where complex computational systems store memory about their environment but also to differentiate between different time points in the past. We show how this extended measure can identify the location of memory related to past experiences in neural networks optimized by deep learning as well as a genetic algorithm.

Sign in / Sign up

Export Citation Format

Share Document