Evolution of Time in Neural Networks: From the Present to the Past, and Forward to the Future

Abstract

What is time? Since the function of the brain is closely tied in with that of time, investigating the origin of time in the brain can help shed light on this question. In this paper, we propose to use simulated evolution of artificial neural networks to investigate the relationship between time and brain function, and the evolution of time in the brain. A large number of neural network models are based on a feedforward topology (perceptrons, backpropagation networks, radial basis functions, support vector machines, etc.), thus lacking dynamics. In such networks, the order of input presentation is meaningless (i.e., it does not affect the behavior) since the behavior is largely reactive. That is, such neural networks can only operate in the present, having no access to the past or the future. However, biological neural networks are mostly constructed with a recurrent topology, and recurrent (artificial) neural network models are able to exhibit rich temporal dynamics, thus time becomes an essential factor in their operation. In this paper, we will investigate the emergence of recollection and prediction in evolving neural networks. First, we will show how reactive, feedforward networks can evolve a memory-like function (rec- Chung, Kwon, Mann, and Choe ollection) through utilizing external markers dropped and detected in the environment. Second, we will investigate how recurrent networks with more predictable internal state trajectory can emerge as an eventual winner in evolutionary struggle when competing networks with less predictable trajectory show the same level of behavioral performance. We expect our results to help us better understand the evolutionary origin of recollection and prediction in neuronal networks, and better appreciate the role of time in brain function.

Time, Consciousness, and Mind Uploading

“…The main technical results summarized in this paper (Sec. 3 and 4) have appeared previously in [Kwon & Choe, 2008;, 2011Chung et al, 2012]. We would like to thank Timothy A. Mann (Texas A&M University) for his feedback on an earlier version of this manuscript.…”

“…Moreover, it can even seem that the brain generates time (in the psychological sense, not in the physical sense) since, without the brain, a living organism cannot have the notion of past nor future (see Dowden [2001] for a discussion on time and mind/brain function). When combined with an evolutionary perspective, this seemingly straight-forward idea that the brain enables the conceptualization of past and future can lead to deeper insights into the principles of brain function (see, e.g., Chung et al [ , 2012; ; Kwon & Choe [2008]).…”

Predictable internal brain dynamics in EEG and its relation to conscious states

“…In our previous computer simulation works, we argued that predictable internal brain dynamic is a necessary condition of consciousness (Kwon and Choe, 2008 ; Choe et al, 2012 ; Chung et al, 2012 ). The argument was based on agency, self-awareness, and high predictability of self-authored actions.…”

A general purpose artificial intelligence framework for the analysis of complex biological systems

“…This type of function has a radial symmetry such as a Gaussian function, which causes the activation of a node to depend on its distance from a center vector, thus allowing it to respond to a local region of feature space. These static feed-forward networks, however, struggle on more complex classifications, and since they are mere input-output devices they cannot detect or produce temporal sequences [36,37].…”

“…However, due to the temporally correlated nature of observations in time-series data the iid assumption becomes unrealistic [37]. Instead, causal dependence among observations is often assumed, such that…”