Title: Design of Web Agents Inspired by Brain Research
1Design of Web Agents Inspired by Brain Research
- Maya Dimitrova, Hiroaki Wagatsuma and Yoko
Yamaguchi - Institute of Control and System Research
Bulgarian Academy of Sciences - Laboratory for Dynamics of Emergent
Intelligence, RIKEN Brain Science Institute, Japan
2Content
- 1. Introduction
- 2. Information retrieval studies based on
cognitive heuristics (problem definition) - 3. Theta phase coding in the brain and episodic
memory - 3.1. The Theta phase model
- 3.2. Relevance to episodic/autobiographical
memory - 4. Autobiographical memory in Web context An
example - 5. Conclusions and future work
3Introduction
- Modeling agents own experience their
reconstructed past - is essential to optimize
agent behavior (i.e. agents for Web knowledge
search, retrieval and presentation) - We propose to base this optimization on recent
studies and models of the brain focusing on the
generality of processing in the animal and human,
not on their difference - We have focused on episodic memory and the
underlying hippocampal mechanisms of processing
as closest to the story-telling approach of
agent design
4Information retrieval studies based on cognitive
heuristics
- Problem statement
- Current Web page classifiers perform excessive
amount of processing to reach simple
classificatory results - Whenever the classificatory task is
multi-dimensional, agent performance deteriorates
dramatically - There is the database or storage problem where
models have always been least analogous to human
memory - Human memory processing is fast, heuristical and
much more efficient in the multi-dimensional
case, than in the sequential processing case
(contrary to the machine) etc. (recent finding) - There is always a point in looking into recent
brain studies for their fast and accelerated
development as empirically-based science
5Information retrieval studies based on cognitive
heuristics (2)
- The current study
- Presents the main ideas of the Theta phase
precession theory as proposing a memory model,
different from the mainstream rate-coding models - Operationalizes episodic memory for the purpose
of design of memory-optimized Web search agent - Provides an example to illustrate the described
process in a human Web search process and some
relevant conclusions for agent future development
6The agent (1)
- In earlier work we designed a Java-servlet (a
wrapper to a search engine) to diagnose the level
of expertise and detail of a corpus of on-line
available Web pages - Weak point what to store in the database and in
what form
7The agent (2)
- It employed pattern classification based on
syntactic analysis for diagnosing the amount of
detail - And cognitive heuristics based on memory research
for the expert level of the text
8The agent (3)
- In following history of interaction, optimization
is needed much the way natural cognitive systems
perform - learn, abstract, remember and forget - We use the autobiographical memory metaphor to
apply to such kind of Web agents and the Theta
phase precession theory to model it
9Current MATLAB GUI versionof the agent interface
- The difference of the MatLab version from the
Java version is that the Java-servlet processed
also the hyperlink structure of the Web page - The current version is simplified for algorithmic
and modeling reasons
10Assumptions of the current study
- Assumptions
- - User interaction with the present-day Web is an
autobiographical experience (remembering
sequences of events like personal-life episodes) - Memorizing events in a human-like memory system
undergoes constant synthesis as any other
learning process and therefore can be implemented
in autonomous agent on the Web
11Operational definitions in the current study
- Definition of Episodic Memory
- The system of processing episodes of Web search
and transforming them into autobiographical
events of successful/unsuccessful Web navigation
to reach the needed goal - Every Web page viewed by the user is a complex
perceptual and semantic stimulus, i.e. an episode
of Web search - What is stored in episodic memory from the rapid
viewing of a succession of pages is a set of
fragments of the search episode rather than the
entire pages and their exact order of viewing
12Hypotheses of the current study
- The theoretical hypothesis is that episodic
memory extracts meaningful cues from the
fragments of the page-retrieval episodes, rather
than random perceptual or semantic cues - Meaningful we define as having anticipatory
value (i.e. useful in the future) - The tested hypothesis is that the mechanisms of
event synthesis from fragments of page-retrieval
episodes are the same in personally-significant
and neutral situations, that is universal for
learning per se - These effects are reproduced by both the human
and the agent in the current study
13Theta phase coding in the brain and episodic
memory
- Theta phase theory models rhythmic patterns of
activity of assemblies of neurons in the brain
and their role in complex cognitive tasks (theta
rhythm 4-10 Hz) - Theta phase modulation is associated with
learning and memory in rats and humans A
mechanism of pattern compression has been
observed in hippocampal neuron assemblies, which
is called theta phase precession - Modelling hippocampal nerve cirquit by the Theta
phase precession theory (Yamaguchi, Yamaguchi et
al.) reinstates complex learning effects observed
in human episodic memory like object-context
integration, single-trial learning and time-space
contextualization
14Neuro-realistic model of episodic encoding and
retrieval
- (a) Main modules of the hippocampus ECII,
ECIII, CA3, CA1, DG - (b) Entorhinal input, emerging from the sensory
system and representing the vector time series
produced by behavior - (c) when the rat runs to the right, the phase
shift in firing within each theta rhythm cycle
occurs in place cells 1 to 4, which are activated
sequentially
15Properties of the phase model
- (The recurrent connections in the CA3 layer of
the hippocampus form asymmetric connections so
that units with prior activations are connected
to those with subsequent activations - These activations are a consequence of the
coincidence between their phase differences and
the time window of the asymmetric synaptic
plasticity
16Model of hippocampal nerve circuit
- (a) mechanism of theta phase coding
- (b) phase shift in firing within each theta
rhythm cycle
17Relevance to modeling memory
- Partial cuing triggers pattern completion in the
CA3 and its transmission to the CA1 and EC. Thus
a stored pattern in the hippocampus can be sent
to the cortical area to replay the input pattern - The temporal difference between encoding and
retrieval in the network parallels behavioral
tests - The retrieval is ten times faster than the
behavioral input in the encoding stage and the
retrieval time scale is similar to that of the
compressed pattern of theta phase precession - The retrieved activity can cause further synaptic
plasticity in other cortical areas for memory
consolidation or memory transfer from the
hippocampus to the cortex
18Importance of theta phase precession theory to
the present study
- The emergence of rhythmic patterns in the absence
of memory to cause its formation is a plausible
candidate for a neural correlate of the formation
of complex and durable cognitive effects
governing future behavior i.e. autobiographical
memories - We have aimed to give a relevant example to
illustrate these effects
19How to find an Art Gallery on the Web with
incomplete initial information?
- Participants
- - Motivated
- - Neutral
- Search goal
- - Example of new concept learning, similar to
artificial concept learning Kurenai Kai - Search task
- - Google search from incomplete initial
information (The name of the gallery Kurenai
Kai not known apriory)
20Results and discussion
Table 1. User performance on Web search with
incomplete initial information about the search
goal
- Our study of Web search has replicated the
mechanism of performance of the theta phase
precession model - The Web paths resemble random search until a
meaningful path is composed - We observe that meaningful paths are composed,
rather than encountered
21Web search Kurenai Kai
- Left path represents the nature of the search
with incomplete initial information - Right path represents the shortest path with
well-remembered concept term
22Remembering meaningful fragments of search
episodes
Left path represents episodic memory guided
retrieval based on a set of meaningful cues and
insight The pages to the right represent the
mappings to the respective initial cues (none of
them are identical)
23Conclusions from the Web search study
- Users base subsequent retrieval of the search
path on remembering the events of their search,
which are the meaningful fragments of knowledge
inside the Web pages, not the exact
page-retrieval episodes - We propose that the autonomous Web agent behaves
in analogy with the event-based
(autobiographical) strategy that Web users are
applying for retrieval of useful information,
which is some state of knowledge with
anticipatory value (useful in the future) - Next will be tests of the agent for optimized
storage of fragments of knowledge contained in
the Web page, rather than of snapshots of
sequences of Web pages
24Fragment extraction and recombination of textual
elements as a process of encoding search events
Agent reinstatement of the search task
25Temporal evolution of episodic events by the
neuro-cognitive agent
26Conclusions and Future Work
- We presented one approach towards the design of
Web agents based on recent knowledge from brain
research - We have tried to demonstrate how the theoretical
framework of theta phase coding endows real-time
process of memory formation of Web search
experiences and the retrieval process of
effective routes to the targets through the
experienced sites - The proposed approach focuses on bridging the gap
between neuroscience and Web technologies - It is currently being applied to retrieval of
cardiological knowledge from the Web
27Acknowledgement
- This work is supported by
- NSRF of the Bulgarian Ministry of Education and
Science as part of the Research Project ? MI -
1509/2005 - Multimodal User and Sensor Interface in a
Computer-Aided System for Cardiological
Diagnosis and Intervention
28 - Thank you
- for your attention