162 Review TRENDS in Cognitive Sciences Vol.6 No.4 April 2002 Episodic memory and (2008)
Lokendra Shastri, Lokendra Shastri
cortico–hippocampal interactions
An extended local connectionist manifesto: Embracing relational and procedural knowledge (2008)
The author has performed an important service by dispelling several myths and misconceptions concerning the localist approach. The localist position and compu-tational model presented in the target...
Connectionist Mechanisms for Cognitive Control (2008)
Carter Wendelken, Lokendra Shastri
An understanding of cognitive control is crucial for understanding high-level cognition and delineating the functional role of prefrontal cortex in supporting complex cognitive operations. In this...
Massively parallel knowledge representation and reasoning: Taking a cue from the brain (2008)
34.4> shruti --- a connectionist knowledge representation and inference system that can encode a large number of facts, rules, and a type hierarchy, and perform a class of first-order inferences...
An extended local connectionist manifesto: Embracing relational and procedural knowledge (2007)
The author has performed an important service by dispelling several myths and misconceptions concerning the localist approach. The localist position and computational model presented in the target...
Lokendra Shastri, Carter Wendelken
coherent explanations--- a fusion of structured connectionism, temporal
The Radical Alternative to Hybrid Systems (2007)
D. S. Blank, M. Coltheart, J. Diederich, B. M. Garner, R. W. Gayler, C. L. Giles, ...
In August 1998 Dave Touretzky asked on the connectionists e-mailing list, "Is connectionist symbol processing dead?". This started a debate, and much interesting discussion...
A Computational Model of Metaphoric Reasoning About Action and Event Descriptions (2007)
Srini Narayanan, Dan Jurafsky, Lokendra Shastri
action FALL -> FAIL OBSTACLE -> DIFFICULTY free-trade moving unregulated P(fall loose_control) moving & obstacle => loose_balance = .6 regained balance stumble lc lc fall fall .8 .2 .01...
Massively parallel knowledge representation and reasoning: Taking a cue from the brain (2007)
Lokendra Shastri And, Lokendra Shastri, D. R. Mani
a connectionist semantic network that can perform inheritance and recognition in time proportional to the depth of the conceptual hierarchy; shruti --- a connectionist knowledge representation and...
Like To, Mitchell Marcus, Mark Steedman, Don Hindle, Tony Kroch, Lokendra Shastri, ...
Description Based Parsing in a Connectionist Network James Brinton Henderson Mitchell Marcus Recent developments in connectionist architectures for symbolic computation have made it possible to...
Handprinted Digit Recognition Using (2007)
Spatiotemporal Connectionist Models, Thomas Fontaine, Lokendra Shastri
We describe a connectionist model for recognizing unconstrained handprinted digits. Instead of treating the input as a static signal, the image is scanned over time and converted into a time-varying...
Graeme S. Halford, William H. Wilson, Steven Phillips, Robert Siegler, John Flavell, Ken Kotovsky, ...
Behavioral & Brain Sciences, target article accepted. This work was supported by grants from the Australian Research Council. The authors would like to give special thanks to Keith Holyoak, whose...
Biological networks are capable of gradual learning based on observing a large number of exemplars over time as well as of rapidly memorizing specific events as a result of a single exposure. The...
We readily acquire memories of events and situations in our daily lives. There is a broad consensus that the hippocampal system (HS) plays a critical role in the encoding and retrieval of such...
Graeme S. Halford, William H. Wilson, Steven Phillips, Robert Siegler, John Flavell, Ken Kotovsky, ...
like to give special thanks to Keith Holyoak, whose continuing interest in the problems and penetrating observations contributed greatly to the development of this work. We would also like to thank...
Spatio-Temporal Neural Networks for Vision, Reasoning and Rapid Decision Making (2006)
A spatio-temporal system for recognizing handprint digit strings was designed and trained to recognize handprinted ZIP codes. The results of our work on a biologically motivated model of reflexive...
Connectionist Mechanisms for Cognitive Control (2005)
Wendelken, Carter, Shastri, Lokendra
An understanding of cognitive control is crucial for understanding high-level cognition and delineating the functional role of prefrontal cortex in supporting complex cognitive operations. In this...
Combining belief and utility in a structured connectionist agent architecture (2002)
Carter Wendelken, Lokendra Shastri
The SHRUTI model demonstrates how a system of simple, neuron-like elements can encode a large body of relational causal knowledge and provide the basis for rapid inference. Here we show how a...
A Computationally Efficient Abstraction of Long-term Potentiation (2002)
A computational abstraction of long-term potentiation (LTP) is proposed. The abstraction captures key temporal and cooperative properties of LTP, and also lends itself to rapid computation. The...
Episodic Memory and Cortico-Hippocampal Interactions (2002)
Lokendra Shastri, Lokendra Shastri
This memory trace is a rather complex neural circuit comprising all the functional subunits discussed in the section on representational requirements of encoding episodic memory, but SMRITI shows...
A computational model of episodic memory formation in the hippocampal system. Neurocomputing (2001)
The memorization of events and situations (episodic memory) requires the rapid formation of a memory trace consisting of several functional components. A computational model is described that...
A Connectionist Model of Planning via Back-chaining Search (2001)
Max Garagnani, Lokendra Shastri, Carter Wendelken
A connectionist model for emergent planning behavior is proposed. The model demonstrates that a simple planning schema, acting in concert with two general purpose cognitive functionalities, namely,...
A connectionist encoding of parameterized schemas and reactive plans (2001)
Lokendra Shastri, Dean J. Grannes, Srini Narayanan, Jerome A. Feldman
Abstract. Wepresent a connectionist realization of parameterized schemas that can model high-level sensory-motor processes and be a candidate representation for implementing reactive behaviors. The...
A connectionist encoding of parameterized schemas and reactive plans (2001)
Lokendra Shastri, Dean Grannes, Srini Narayanan, Jerome Feldman
We present a connectionist realization of parameterized schemas that can model highlevel sensory-motor processes and be a candidate representation for implementing reactive behaviors. The...
A Connectionist Model of Planning Via Back-Chaining Search (2001)
Max Garagnani Lokendra, Lokendra Shastri, Carter Wendelken
Great advances have marked the progress of AI planning research over the past few years. Recent systems can quickly solve problems that are orders of magnitude harder than those tackled by the best...
Marvin S. Cohen, Bryan B. Thompson, Leonard Adelman, Terry A. Bresnick, Lokendra Shastri, Sharon L. Riedel, ...
Contract No. DASW01-97-C-0038 The views, opinions, and/or findings contained in this report are those of the authors and should not be construed as an official Department of the Army position,...
Marvin S. Cohen, Bryan B. Thompson, Leonard Adelman, Terry A. Bresnick, Lokendra Shastri, Sharon L. Riedel, ...
Contract No. DASW01-97-C-0038 The views, opinions, and/or findings contained in this report are those of the authors and should not be construed as an official Department of the Army position,...
Probabilistic inference and learning in a connectionist causal network (2000)
Carter Wendelken, Lokendra Shastri
The SHRUTI model demonstrates how a structured connectionist network can be used to encode relational causal knowledge and provide a basis for rapid inference. This paper explores the extent to which...
Lokendra Shastri, Carter Wendelken
A connectionist model capable of performing rapid inferences to establish explanatory and referential coherence is described. The model's ability to perform such inferences arises from (i) its...
Automatic phonetic transcription of spontaneous speech (American English (2000)
Shuangyu Chang, Lokendra Shastri, Steven Greenberg
An automatic transcription system has been developed to label and segment phonetic constituents of spontaneous American English without benefit of a word-level transcript. Instead, special-purpose...
In order to understand language, a hearer must draw inferences to establish referential and causal coherence. Hence our abilityto understand language suggests that we are capable of performing a wide...
We are capable of drawing a variety of inferences effortlessly, spontaneously, and with remarkable efficiency — as though these inferences are a reflex response of our cognitive apparatus. This...
Recruitment of binding and binding-error detector circuits via long-term potentiation (1999)
potentiation
Knowledge fusion in the large: Taking a cue from the brain (1999)
Lokendra Shastri, Carter Wendelken
Abstract Even the most commonplace cognitive behaviors suchas vision and languageunderstandinginvolve large-scale fusion of disparate pieces of evidence. Therefore, our capacity to rapidly and...
Syllable Detection And Segmentation Using Temporal Flow Neural Networks (1999)
Lokendra Shastri, Shuangyu Chang, Steven Greenberg
The syllable serves as an important interface between the lowerlevel (phonetic and phonological) and the higher-level (morphological and lexical) representational tiers of language. It has been...
Lokendra Shastri, Carter Wendelken
Understanding language is the quintessential softcomputing problem. In order to understand language, a hearer must integrate a wide array of fuzzy, incomplete, and common sense knowledge. Yet we...
Recruitment of Binding and Binding-Error Detector Circuits Via Long-Term Potentiation (1999)
The memorization of events and situations (episodic memory) requires the rapid formation of neural circuits for detecting bindings and binding-errors. The formation of binding-error detectors,...
A Spatiotemporal Connectionist Model of Algebraic Rule-Learning (1999)
A Spatiotemporal Connectionist, Lokendra Shastri, Shawn Chang
Recent experiments by Marcus, Vijaya, Rao, and Vishton suggest that infants are capable of extracting and using abstract algebraic rules such as "the first item X is the same as the third item...
A Biological Grounding of Recruitment Learning and Vicinal Algorithms (1999)
Biological neural networks are capable of gradual learning based on observing a large number of exemplars over time as well as rapidly memorizing specific events as a result of a single exposure. The...
Connectionist Symbol Processing: Dead or Alive? (1999)
D. S. Blank, M.S. Cohen, M. Coltheart, J. Diederich, B. M. Garner, R.W. Gayler, ...
this article are of varying nature: position summaries, individual research summaries, historical accounts, discussion of controversial issues, etc. We have not attempted to connect the various...
Syllable detection and segmentation using temporal flow neural networks (1999)
Lokendra Shastri, Shuangyu Chang, Steven Greenberg
The syllable serves as an important interface between the lowerlevel (phonetic and phonological) and the higher-level (morphological and lexical) representational tiers of language. It has been...
Lokendra Shastri, Carter Wendelken
Understanding language is the quintessential softcomputing problem. In order to understand language, a hearer must integrate a wide array of fuzzy, incomplete, and common sense knowledge. Yet we...
Soft Computing in SHRUTI: --- A neurally plausible model of reflexive (1999)
Reasoning And Relational, Lokendra Shastri, Carter Wendelken
Understanding language is the quintessential softcomputing problem. In order to understand language, a hearer must integrate a wide array of fuzzy, incomplete, and common sense knowledge. Yet we...
Lokendra Shastri And, Lokendra Shastri, Carter Wendelken
Understanding language is the quintessential soft-computing problem. In order to understand language,a hearer must integrate a wide array of fuzzy, incomplete, and common sense knowledge. Yet we...
Syllable detection and segmentation using temporal flow neural networks (1999)
Lokendra Shastri, Shuangyu Chang, Steven Greenberg
The syllable serves as an important interface between the lowerlevel (phonetic and phonological) and the higher-level (morphological and lexical) representational tiers of language. It has been...
A Connectionist System for Rule Based Reasoning with Multi-Place Predicates and Variables. (1998)
Shastri, Lokendra, Ajjanagadde, Venkat
McCarthy has observed that the representational power of most connectionist systems is restricted to unary predicates applied to a fixed object. More recently, Fodor and Pylyshyn have made a sweeping...
The Relevance of Connectionism to AI: A Representation and Reasoning Perspective. (1998)
In this paper it is argued that not only is connectionism relevant to knowledge representation and reasoning, but it also provides an ideal computational architecture for intelligent systems. To...
Massively Parallel Simulation of Structured Connectionist Networks. (1998)
Mani, D. R., Shastri, Lokendra
We map structured connectionist models of knowledge representation and reasoning onto existing general purpose massively parallel architectures with the objective of developing and implementing...
We are capable of drawing a variety of inferences effortlessly, spontaneously, and with remarkable efficiency --- as though these inferences are a reflex response of our cognitive apparatus. This...
Incremental Class Learning approach and its application to Handwritten Digit Recognition (1998)
Jacek Ma'ndziuk, Lokendra Shastri
Incremental Class Learning (ICL) provides a feasible framework for the development of scalable learning systems. Instead of learning a complex problem at once, ICL focuses on learning subproblems...
Incremental Class Learning approach and its application to Handwritten Digit Recognition (1998)
Jacek Ma'ndziuk, Lokendra Shastri
Incremental Class Learning (ICL) provides a feasible framework for the development of scalable learning systems. Instead of learning a complex problem at once, ICL focuses on learning subproblems...
Spatio-Temporal Neural Networks for Vision, Reasoning and Rapid Decision Making. (1997)
The results of our work on a biologically motivated model of reflexive reasoning were used to implement a large scale system for performing rapid reasoning using very large knowledge bases. The...
It is argued that the memorization of events and situations (episodic memory) requires the rapid formation of neural circuits responsive to binding errors and binding matches. While the formation of...
A Model of Rapid Memory Formation in the Hippocampal System (1997)
Our ability to remember events and situations in our daily life demonstrates our ability to rapidly acquire new memories. There is a broad consensus that the hippocampal system (HS) plays a critical...
A Connectionist Encoding of Parameterized Schemas and Reactive Plans (1997)
Lokendra Shastri, Dean J. Grannes, Srini Narayanan, Jerome A. Feldman
. We present a connectionist realization of parameterized schemas that can model high-level sensory-motor processes and be a candidate representation for implementing reactive behaviors. The...
A Connectionist Encoding of Schemas and Reactive Plans (1997)
Lokendra Shastri, Dean J. Grannes, Srini Narayanan, Jerome A. Feldman
We describe a connectionist encoding of schemas and reactive plans that can model high-level sensory-motor processes and can be a candidate representation for implementing reactive behaviors. The...
Exploiting Temporal Binding to Learn Relational Rules Within a Connectionist Network (1997)
Rules encoded by traditional rule-based systems are brittle and inflexible because it is difficult to specify the precise conditions under which a rule should fire. If the conditions are made too...
Claudio Privitera And, Claudio M. Privitera, Lokendra Shastri
Any intelligent system, whether human or robotic, must be capable of dealing with patterns over time. Temporal pattern processing can be achieved if the system has a short-term memory capacity (STM)...
A Connectionist Treatment of Negation and Inconsistency (1996)
Lokendra Shastri, Dean J. Grannes
A connectionist model capable of encoding positive as well as negated knowledge and using such knowledge during rapid reasoning is described. The model explains how an agent can hold inconsistent...
shruti. (ii) Whereas "signatures" have semantic content, "synchrony" does not. This lack of semantic content would make learning more difficult in the synchronous activation...
Temporal Compositional Processing by a DSOM Hierarchical Model (1996)
Claudio M. Privitera, Lokendra Shastri
. Any intelligent system, whether human or robotic, must be capable of dealing with patterns over time. Temporal pattern processing can be achieved if the system has a short-term memory capacity...
Claudio Privitera And, Claudio M. Privitera, Lokendra Shastri
Any intelligent system, whether human or robotic, must be capable of dealing with patterns over time. Temporal pattern processing can be achieved if the system has a short-term memory capacity (STM)...
A connectionist treatment of negation and inconsistency (1996)
Lokendra Shastri, Dean J. Grannes
A connectionist model capable of encoding positive as well as negated knowledge and using such knowledge during rapid reasoning is described. The model explains how an agent can hold inconsistent...
Recognizing Handwritten Digit Strings Using Modular Spatio-temporal Connectionist Networks (1995)
Lokendra Shastri, Thomas Fontaine
We describe an alternate approach to visual recognition of handwritten words, wherein an image is converted into a spatio-temporal signal by scanning it in one or more directions, and processed by a...
Lokendra Shastri, Dean Jeffrey Grannes
Recently, shruti has been proposed as a connectionist model of rapid reasoning. It demonstrates how a network of simple neuron-like elements can encode a large number of specific facts as well as...
Massively Parallel Simulation of Structured Connectionist Networks: An Interim Report (1994)
We map structured connectionist models of knowledge representation and reasoning onto existing general purpose massively parallel architectures with the objective of developing and implementing...
Massively Parallel Real-Time Reasoning with Very Large Knowledge Bases: An Interim Report (1994)
We map structured connectionist models of knowledge representation and reasoning onto existing general purpose massively parallel architectures with the objective of developing and implementing...
Dietz, Paul, Krizanc, Danny, Rajasekaran, Sanguthevar, Shastri, Lokendra
In this paper we prove a lower bound of Ω(n log n) for the common element problem on two sets of size n each. Two interesting consequences of this lower bound are also discussed. In particular, we...
Lokendra Shastri, Venkat Ajjanagadde
Abstract: Human agents draw a variety of inferences effortlessly, spontaneously, and with remarkable efficiency — as though these inferences are a reflex response of their cognitive apparatus....
A Computational Model of Tractable Reasoning - taking inspiration from cognition (1993)
Polynomial time complexity is the usual `threshold' for distinguishing the tractable from the intractable and it may seem reasonable to adopt this notion of tractability in the context of...
Recognizing Handprinted Digit Strings: a Hybrid Connectionist/Procedural Approach (1993)
Thomas Fontaine, Lokendra Shastri
We describe an alternative approach to handprinted word recognition using a hybrid of procedural and connectionist techniques. We utilize two connectionist components: one to concurrently make...
A computational model of tractable reasoning - taking inspiration from cognition (1993)
Polynomial time complexity is the usual ‘threshold’ for distinguishing the tractable from the intractable and it may seem reasonable to adopt this notion of tractability in the context of...
Character Recognition Using A Modular Spatiotemporal Connectionist Model (1992)
Fontaine, Thomas, Shastri, Lokendra
We describe a connectionist model for recognizing handprinted characters. Instead of treating the input as a static signal, the image is scanned over time and converted into a time-varying signal....
Multiple Instantiation of Predicates in a Connectionist Rule-Based Reasoner (1992)
Shastri and Ajjanagadde have described a neurally plausible system for knowledge representation and reasoning that can represent systematic knowledge involving n-ary predicates and variables, and...
A connectionist solution to the multiple instantiation problem using temporal synchrony (1992)
Shastri and Ajjanagadde have described a neurally plausible system for knowledge representation and reasoning that can represent systematic knowledge involving n-ary predicates and variables, and...
Multiple Instantiation of Predicates in a Connectionist Rule-Based Reasoner (1992)
Shastri and Ajjanagadde have described a neurally plausible system for knowledge representation and reasoning that can represent systematic knowledge involving n-ary predicates and variables, and...
Combining a Connectionist Type Hierarchy with a Connectionist Rule-Based Reasoner (1992)
This paper describes an efficient connectionist knowledge representation and reasoning system that combines rule-based reasoning with reasoning about inheritance and classification within an IS-A...
Combining a Connectionist Type Hierarchy with a Connectionist Rule-Based Reasoner (1991)
This paper describes an efficient connectionist knowledge representation and reasoning system that combines rule-based reasoning with reasoning about inheritance and classification within an IS-A...
Combining a Connectionist Type Hierarchy with a Connectionist Rule-Based Reasoner (1991)
This paper describes an efficient connectionist knowledge representation and reasoning system that combines rule-based reasoning with reasoning about inheritance and classification within an IS-A...
Combining a Connectionist Type Hierarchy with a Connectionist Rule-Based Reasoner (1991)
Mani Lokendra, D. R. Mani, Lokendra Shastri
This paper describes an efficient connectionist knowledge representation and reasoning system that combines rule-based reasoning with reasoning about inheritance and classification within an IS-A...
Shastri, Lokendra, Ajjanagadde, Venkat
Human agents draw a variety of inferences effortlessly, spontaneously, and with remarkable efficiency - as though these inferences are a reflex response of their cognitive apparatus. The work...
The Relevance of Connectionism to AI: A Representation and Reasoning Perspective (1989)
It is generally acknowledged that tremendous computational activity underlies some of the most commonplace cognitive behavior. If we view these computations as systematic rule governed operations...
A Connectionist System for Rule Based Reasoning with Multi-Place Predicates and Variables (1989)
Shastri, Lokendra, Ajjanagadde, Venkat
McCarthy has observed that the representational power of most connectionist systems is restricted to unary predicates applied to a fixed object. More recently, Fodor and Pylyshyn have made a sweeping...
Evidential Reasoning in Semantic Networks: A Formal Theory and its Parallel Implementation (1985)
Ph.S. Thesis, Computer Science Dept., U. Rochester; Prof Jerome A. Feldman, thesis advisor; simultaneously published in the Technical Report series.
Vita.
"September 1985."
Evidential reasoning in semantic networks : a formal theory and its parallel implementation / (1985)
Thesis (Ph. D.)--University of Rochester, 1985.
Evidential reasoning in semantic networks : a formal theory and its parallel implementation / (1985)
"September 1985."
Evidential reasoning in semantic networks : a formal theory and its parallel implementation / (1985)
Thesis (Ph. D.)--University of Rochester, 1985.
A Connectionist Solution to the Multiple Instantiation Problem using Temporal Synchrony
Shastri and Ajjanagadde have described a neurally plausible system for knowledge representation and reasoning that can represent systematic knowledge involving n-ary predicates and variables, and...