Here is the essence of the theory: When one encounters a new situation (or makes a substantial change in one's view of the present problem) one selects from memory a structure called a Frame. This is a remembered framework to be adapted to fit reality by changing details as necessary.
A frame is a data-structure for representing a stereotyped situation, like being in a certain kind of living room, or going to a child's birthday party."
– from A Framework for Representing Knowledge. By Marvin Minsky. MIT- AI Laboratory Memo 306, June, 1974. Reprinted in The Psychology of Computer Vision, P. Winston (Ed.), McGraw-Hill, 1975. Shorter versions in J. Haugeland, Ed., Mind Design, MIT Press, 1981, and in Cognitive Science, Collins, Allan and Edward E. Smith (eds.) Morgan-Kaufmann, 1992.
Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian inference provides a principled method for model selection and it converges on the same posterior for both off-line (i.e. batch) and online learning. However, maintaining a parameter posterior for each model in parallel has in general an even higher memory cost than storing the entire data set and is consequently clearly unfeasible. Alternatively, maintaining only a limited set of models in memory could limit memory requirements. However, sufficient statistics for one model will usually be insufficient for fitting a different kind of model, meaning that the agent loses information with each model change. We propose that episodic memory can circumvent the challenge of limited memory-capacity online model selection by retaining a selected subset of data points. We design a method to compute the quantities necessary for model selection even when the data is discarded and only statistics of one (or few) learnt models are available. We demonstrate on a simple model that a limited-sized episodic memory buffer, when the content is optimised to retain data with statistics not matching the current representation, can resolve the fundamental challenge of online model selection.
Dogs have a remarkable ability to recall events from the past, in a similar way to humans. That's according to a new study which found evidence canines have a similar'episodic memory' to their human counterparts. Dogs can recall a person's actions even when they do not expect to have their memory tested, says the research. Previously, evidence that animals use episodic memory has been hard to come by, as it's impossible to ask an animal, in this case a dog, what they remember (stock image) Dogs trained using the trick can watch a person perform an action and carry out the action themselves. For example, if the their owner jumps in the air and then gives the command'do it', the dog would jump in the air.
We present the first probabilistic model to capture all levels of the Minsky Frame structure, with the goal of corpus-based induction of scenario definitions. Our model unifies prior efforts in discourse-level modeling with that of Fillmore's related notion of frame, as captured in sentence-level, FrameNet semantic parses; as part of this, we resurrect the coupling among Minsky's frames, Schank's scripts and Fillmore's frames, as originally laid out by those authors. Empirically, our approach yields improved scenario representations, reflected quantitatively in lower surprisal and more coherent latent scenarios.
There is not much evaluation technique of coimagination method, which is one of the group conversation techniques have been proposed for the purpose of cognitive function training. As one of the indicator of usefulness of cognitive function training, episodic memory is usable. Therefore we have proposed an analytical method for measuring the utilization of episodic memory in coimaginaiton method. Thereafter, We conducted the experiment of group conversation base on walking around in order to give the common experience to the participants, and analyzed the results by the proposed method. In consequence, it is revealed the occurrence of past episodic memory. Furthermore, it indicates individual difference of episodic memory utilization quantitatively in terms of memory taxonomy.
For the past ten years we have been working on the problem of getting a computer to understand natural language. We built an early version of a parser that mapped from English into a language-free representation of the meaning of input sentences (Schank and Tesler, 1969). Simultaneously we worked on the meaning representation itself. We developed Conceptual Dependency which represents meaning as a network of concepts independent of the actual words that might be used to express those concepts (Schank, 1969). Over the years the parser and the representation evolved as we began to understand the complexity of the problem with which we were dealing.
Episodic memory endows agents with numerous general cognitive capabilities, such as action modeling and virtual sensing. However, for long-lived agents, there are numerous unexplored computational challenges in supporting useful episodic-memory functions while maintaining real-time reactivity. In this paper, we review the implementation of episodic memory in Soar and present an expansive evaluation of that system. We demonstrate useful applications of episodic memory across a variety of domains, including games, mobile robotics, planning, and linguistics. In these domains, we characterize properties of environments, tasks, and episodic cues that affect performance, and evaluate the ability of Soar’s episodic memory to support hours to days of real-time operation.
Evidence indicates that episodic memory plays an important role in general cognition. A modest body of research exists for creating artificial episodic memory systems. To date, research has focused on exploring their benefits. As a result, existing episodic memory systems rely on a small, relevant memory cue for effective memory retrieval. We present Ziggurat, a domain-independent episodic memory structure and accompanying episodic learning algorithm that learns the temporal context of recorded episodes. Ziggurat's context-based memory retrieval means that it does not have to rely on relevant agent cues for effective memory retrieval; it also allows an agent to dynamically make plans using past experiences. In our experimental trials in two different domains, Ziggurat performs as well or better than an episodic memory implementation based on most other systems.
The phenomenon of episodic memory has been studied for over thirty years, but it is only recently that its constructive nature has been shown to be closely linked to the processes underpinning imagination. This paper builds on recent work by the authors in developing architectures for a form of imagination suitable for use in artifacts, and considers how these architectures might be extended to provide a form of episodic memory.
A major limitation of today's computer games is the shallowness of interactions with non-player characters. To build up relationships with players, NPCs should be able to remember shared experiences, including conversations, and shape their responses accordingly. We believe that progress in AI has already reached the point where research on using NLP and large KBs in games could lead to important new capabilities. We describe our Listener Architecture for conversational games, which has been implemented in a toolkit used to make short experimental games. Episodic memory plays a central role, using analogical reasoning over a library of previous conversations with the player. Examples and scale-up issues are discussed.