Symbolic Computation Using Cellular Automata-Based Hyperdimensional Computing

This letter introduces a novel framework of reservoir computing that is capable of both connectionist machine intelligence and symbolic computation. A cellular automaton is used as the reservoir of dynamical systems. Input is randomly projected onto the initial conditions of automaton cells, and nonlinear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the reservoir. The proposed framework is shown to be capable of long-term memory, and it requires orders of magnitude less computation compared to echo state networks. As the focus of the letter, we suggest that binary reservoir feature vectors can be combined using Boolean operations as in hyperdimensional computing, paving a direct way for concept building and symbolic processing. To demonstrate the capability of the proposed system, we make analogies directly on image data by asking, What is the automobile of air?

Download Full-text

Soft-wired long-term memory in a natural recurrent neuronal network

10.1101/2020.04.01.020180 ◽

2020 ◽

Author(s):

Miguel A. Casal ◽

Santiago Galella ◽

Oscar Vilarroya ◽

Jordi Garcia-Ojalvo

Keyword(s):

Neuronal Network ◽

Neuronal Networks ◽

Initial Conditions ◽

Permutation Entropy ◽

Long Term Memory ◽

Term Memory ◽

C Elegans ◽

Living Organisms ◽

Recurrent Connections

Neuronal networks provide living organisms with the ability to process information. They are also characterized by abundant recurrent connections, which give rise to strong feed-back that dictates their dynamics and endows them with fading (short-term) memory. The role of recurrence in long-term memory, on the other hand, is still unclear. Here we use the neuronal network of the roundworm C. elegans to show that recurrent architectures in living organisms can exhibit long-term memory without relying on specific hard-wired modules. A genetic algorithm reveals that the experimentally observed dynamics of the worm’s neuronal network exhibits maximal complexity (as measured by permutation entropy). In that complex regime, the response of the system to repeated presentations of a time-varying stimulus reveals a consistent behavior that can be interpreted as soft-wired long-term memory.A common manifestation of our ability to remember the past is the consistence of our responses to repeated presentations of stimuli across time. Complex chaotic dynamics is known to produce such reliable responses in spite of its characteristic sensitive dependence on initial conditions. In neuronal networks, complex behavior is known to result from a combination of (i) recurrent connections and (ii) a balance between excitation and inhibition. Here we show that those features concur in the neuronal network of a living organism, namely C. elegans. This enables long-term memory to arise in an on-line manner, without having to be hard-wired in the brain.

Download Full-text

Towards Fluid Machine Intelligence: Can We Make a Gifted AI?

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33019760 ◽

2019 ◽

Vol 33 ◽

pp. 9760-9764

Author(s):

Ian Davidson ◽

Peter B. Walker

Keyword(s):

School Districts ◽

Fluid Intelligence ◽

Machine Intelligence ◽

Long Term Memory ◽

Specific Knowledge ◽

Current Form ◽

Crystallized Intelligence ◽

Meta Learning ◽

Gifted Education Programs

Most applications of machine intelligence have focused on demonstrating crystallized intelligence. Crystallized intelligence relies on accessing problem-specific knowledge, skills and experience stored in long term memory. In this paper, we challenge the AI community to design AIs to completely take tests of fluid intelligence which assess the ability to solve novel problems using problem-independent solving skills. Tests of fluid intelligence such as the NNAT are used extensively by schools to determine entry into gifted education programs. We explain the differences between crystallized and fluid intelligence, the importance and capabilities of machines demonstrating fluid intelligence and pose several challenges to the AI community, including that a machine taking such a test would be considered gifted by school districts in the state of California. Importantly, we show existing work on seemingly related fields such as transfer, zero-shot, life-long and meta learning (in their current form) are not directly capable of demonstrating fluid intelligence but instead are task-transductive mechanisms.

Download Full-text

Using Short and Long Term Memory to induce environmental information from simple events

Robotica ◽

10.1017/s0263574700007086 ◽

1992 ◽

Vol 10 (1) ◽

pp. 65-74

Author(s):

John L. Gordon ◽

David Williams ◽

Alan Hobson

Keyword(s):

Performance Measure ◽

Memory Models ◽

Machine Intelligence ◽

Long Term Memory ◽

Term Memory ◽

Control Scheme ◽

Computer Based ◽

Short And Long Term ◽

Movement Sensors

SummaryThis paper considers the use of memory models and machine intelligence, to dynamically update a computer based representation of the occupancy of a small building. The input to the model is derived from very simple, single bit, movement sensors in each room of the premises.I It will be shown that the information derived from these sensors can provide adequate data for a building control scheme.Short and Long Term memory models of man will be briefly reviewed. Working models for Short and Long Term memory will be discussed, which have evolved from the earlier work but which have been tuned to fit the machine level constraints of this type of application.A review of the performance of a working pilot installation will be given. A performance measure will be derived and initial figures using this measure will be presented.

Download Full-text

Importin-7 mediates memory consolidation through regulation of nuclear translocation of training-activated MAPK in Drosophila

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.1520401113 ◽

2016 ◽

Vol 113 (11) ◽

pp. 3072-3077 ◽

Cited By ~ 10

Author(s):

Qian Li ◽

Xuchen Zhang ◽

Wantong Hu ◽

Xitong Liang ◽

Fang Zhang ◽

...

Keyword(s):

Memory Consolidation ◽

Mushroom Body ◽

Time Course ◽

Nuclear Translocation ◽

Time Window ◽

Image Data ◽

Nuclear Accumulation ◽

Long Term Memory ◽

Behavioral Impact

Translocation of signaling molecules, MAPK in particular, from the cytosol to nucleus represents a universal key element in initiating the gene program that determines memory consolidation. Translocation mechanisms and their behavioral impact, however, remain to be determined. Here, we report that a highly conserved nuclear transporter, Drosophila importin-7 (DIM-7), regulates import of training-activated MAPK for consolidation of long-term memory (LTM). We show that silencing DIM-7 functions results in impaired LTM, whereas overexpression of DIM-7 enhances LTM. This DIM-7–dependent regulation of LTM is confined to a consolidation time window and in mushroom body neurons. Image data show that bidirectional alteration in DIM-7 expression results in proportional changes in the intensity of training-activated MAPK accumulated within the nuclei of mushroom body neurons during LTM consolidation. Such DIM-7–regulated nuclear accumulation of activated MAPK is observed only in the training specified for LTM induction and determines the amplitude, but not the time course, of memory consolidation.

Download Full-text

Conceptual short-term memory (CSTM) supports core claims of Christiansen and Chater

Behavioral and Brain Sciences ◽

10.1017/s0140525x15000928 ◽

2016 ◽

Vol 39 ◽

Author(s):

Mary C. Potter

Keyword(s):

Working Memory ◽

Rapid Serial Visual Presentation ◽

Language Comprehension ◽

Short Term Memory ◽

Visual Presentation ◽

Long Term Memory ◽

Short Term ◽

Term Memory ◽

Use Of Knowledge

AbstractRapid serial visual presentation (RSVP) of words or pictured scenes provides evidence for a large-capacity conceptual short-term memory (CSTM) that momentarily provides rich associated material from long-term memory, permitting rapid chunking (Potter 1993; 2009; 2012). In perception of scenes as well as language comprehension, we make use of knowledge that briefly exceeds the supposed limits of working memory.

Download Full-text

Comparison of Auditory, Language, Memory, and Attention Abilities in Children With and Without Listening Difficulties

American Journal of Audiology ◽

10.1044/2020_aja-20-00018 ◽

2020 ◽

Vol 29 (4) ◽

pp. 710-727

Author(s):

Beula M. Magimairaj ◽

Naveen K. Nagaraj ◽

Alexander V. Sergeev ◽

Natalie J. Benafield

Keyword(s):

Auditory Processing ◽

Short Term Memory ◽

Group Differences ◽

Long Term Memory ◽

Short Term ◽

Significant Group ◽

Term Memory ◽

Memory And Attention ◽

Speed And Accuracy

Objectives School-age children with and without parent-reported listening difficulties (LiD) were compared on auditory processing, language, memory, and attention abilities. The objective was to extend what is known so far in the literature about children with LiD by using multiple measures and selective novel measures across the above areas. Design Twenty-six children who were reported by their parents as having LiD and 26 age-matched typically developing children completed clinical tests of auditory processing and multiple measures of language, attention, and memory. All children had normal-range pure-tone hearing thresholds bilaterally. Group differences were examined. Results In addition to significantly poorer speech-perception-in-noise scores, children with LiD had reduced speed and accuracy of word retrieval from long-term memory, poorer short-term memory, sentence recall, and inferencing ability. Statistically significant group differences were of moderate effect size; however, standard test scores of children with LiD were not clinically poor. No statistically significant group differences were observed in attention, working memory capacity, vocabulary, and nonverbal IQ. Conclusions Mild signal-to-noise ratio loss, as reflected by the group mean of children with LiD, supported the children's functional listening problems. In addition, children's relative weakness in select areas of language performance, short-term memory, and long-term memory lexical retrieval speed and accuracy added to previous research on evidence-based areas that need to be evaluated in children with LiD who almost always have heterogenous profiles. Importantly, the functional difficulties faced by children with LiD in relation to their test results indicated, to some extent, that commonly used assessments may not be adequately capturing the children's listening challenges. Supplemental Material https://doi.org/10.23641/asha.12808607

Download Full-text

Retrieval from Memory or Procedural Strategies for Addition Problems

Swiss Journal of Psychology ◽

10.1024/1421-0185/a000036 ◽

2011 ◽

Vol 70 (1) ◽

pp. 35-39 ◽

Cited By ~ 3

Author(s):

Muriel Fanget ◽

Catherine Thevenot ◽

Caroline Castel ◽

Michel Fayol

Keyword(s):

Reaction Times ◽

Long Term Memory ◽

Verbal Reports ◽

Term Memory ◽

Simple Addition ◽

Memory Traces ◽

Addition Problem ◽

Retrieval From Memory ◽

Calculation Procedures

In this study, we used a paradigm recently developed ( Thevenot, Fanget, & Fayol, 2007 ) to determine whether 10-year-old children solve simple addition problems by retrieval of the answer from long-term memory or by calculation procedures. Our paradigm is unique in that it does not rely on reaction times or verbal reports, which are known to potentially bias the results, especially in children. Rather, it takes advantage of the fact that calculation procedures degrade the memory traces of the operands, so that it is more difficult to recognize them when they have been involved in the solution of an addition problem by calculation rather than by retrieval. The present study sharpens the current conclusions in the literature and shows that, when the sum of addition problems is up to 10, children mainly use retrieval, but when it is greater than 10, they mainly use calculation procedures.

Download Full-text

The Acute Effect of Alcohol on Various Memory Processes

Journal of Psychophysiology ◽

10.1027/0269-8803/a000038 ◽

2010 ◽

Vol 24 (4) ◽

pp. 249-252 ◽

Cited By ~ 7

Author(s):

Márk Molnár ◽

Roland Boha ◽

Balázs Czigler ◽

Zsófia Anna Gaál

Keyword(s):

Low Dose ◽

Short Term Memory ◽

Acute Effect ◽

Long Term Memory ◽

Term Memory ◽

Memory Processes ◽

Different Types ◽

The Brain ◽

Legal Consequences

This review surveys relevant and recent data of the pertinent literature regarding the acute effect of alcohol on various kinds of memory processes with special emphasis on working memory. The characteristics of different types of long-term memory (LTM) and short-term memory (STM) processes are summarized with an attempt to relate these to various structures in the brain. LTM is typically impaired by chronic alcohol intake but according to some data a single dose of ethanol may have long lasting effects if administered at a critically important age. The most commonly seen deleterious acute effect of alcohol to STM appears following large doses of ethanol in conditions of “binge drinking” causing the “blackout” phenomenon. However, with the application of various techniques and well-structured behavioral paradigms it is possible to detect, albeit occasionally, subtle changes of cognitive processes even as a result of a low dose of alcohol. These data may be important for the consideration of legal consequences of low-dose ethanol intake in conditions such as driving, etc.

Download Full-text

Visual Search Facilitation in Repeated Displays Depends on Visuospatial Working Memory

Experimental Psychology (formerly Zeitschrift für Experimentelle Psychologie) ◽

10.1027/1618-3169/a000125 ◽

2012 ◽

Vol 59 (1) ◽

pp. 47-54 ◽

Cited By ~ 16

Author(s):

Angela A. Manginelli ◽

Franziska Geringswald ◽

Stefan Pollmann

Keyword(s):

Working Memory ◽

Visual Search ◽

Control Experiment ◽

Memory Load ◽

Contextual Cueing ◽

Long Term Memory ◽

Visuospatial Working Memory ◽

Working Memory Load ◽

Memory Resources

When distractor configurations are repeated over time, visual search becomes more efficient, even if participants are unaware of the repetition. This contextual cueing is a form of incidental, implicit learning. One might therefore expect that contextual cueing does not (or only minimally) rely on working memory resources. This, however, is debated in the literature. We investigated contextual cueing under either a visuospatial or a nonspatial (color) visual working memory load. We found that contextual cueing was disrupted by the concurrent visuospatial, but not by the color working memory load. A control experiment ruled out that unspecific attentional factors of the dual-task situation disrupted contextual cueing. Visuospatial working memory may be needed to match current display items with long-term memory traces of previously learned displays.

Download Full-text