Archive

Archive for January, 2016

No QuEST Meeting, 29 Jan

January 28, 2016 Leave a comment

Due to Capt Amerika’s travel schedule, there will be no meeting this week.  We plan to resume our regular schedule next week.

Advertisements
Categories: Uncategorized

Weekly QuEST Discussion Topics and News, 22 Jan

January 21, 2016 Leave a comment

QuEST 22 Jan 2016:

We will finish this week the material from the Kabrisky Memorial Lecture for 2016: ‘What is QuEST?’  As all QuEST meetings this will be an interactive discussion of the material so anyone who has never been exposed to our effort can catch up and those who have been involved can refine their personal views on what we seek – last week we got through the dual process model part of the discussion – we will pick up there (hitting the Theory of consciousness – the link game – exformation – gist – narratives – events –  and hit some results (Dube, Derriso, Vaughn)) – there was also some new discussion on the theoretical framework (math) so we’ve inserted a new slide there

QuEST – Qualia Exploitation of Sensing Technology – a Cognitive exoskeleton

PURPOSE

 

– QuEST is an innovative analytical and software development approach to improve human-machine team decision quality over a wide range of stimuli (handling unexpected queries) by providing computer-based decision aids that are engineered to provide both intuitive reasoning and “conscious” deliberative thinking.

 

– QuEST provides a mathematical framework to understand what can be known by a group of people and their computer-based decision aids about situations to facilitate prediction of when more people (different training) or computer aids are necessary to make a particular decision.

 

 

DISCUSSION

 

– QuEST defines a new set of processes that will be implemented in computer agents.

 

– Decision quality is dominated by the appropriate level of situation awareness.  Situation awareness is the perception of environmental elements with respect to time/space, logical connection, comprehension of their meaning, and the projection of their future status.

 

– QuEST is an approach to situation assessment (processes that are used to achieve situation awareness) and situation understanding (comprehension of the meaning of the information) integrated with each other and the decision maker’s goals.

 

– QuEST solutions help humans understand the “so what” of the data {sensemaking ~ “a motivated, continuous effort to understand connections (among people, places and events) in order to anticipate their trajectories and act effectively” for decision quality performance}.1

 

– QuEST agents implement blended dual process cognitive models (have both artificial conscious and artificial subconscious/intuition processes) for situation assessment.

 

— Artificial conscious processes implement in working memory the QuEST Theory of Consciousness (structural coherence, situation based, simulation/cognitively decoupled).

 

— Subconscious/intuition processes do not use working memory and are thus considered autonomous (do not require consciousness to act) – current approaches to data driven, artificial intelligence provide a wide range of options for implementing instantiations of capturing experiential knowledge used by these processes.

 

– QuEST is developing a ‘Theory of Knowledge’ to provide the theoretical foundations to understand what an agent or group of agents can know, which fundamentally changes human-computer decision making from an empirical effort to a scientific effort.

 

1 Klein, G., Moon, B. and Hoffman, R.R., “Making Sense of Sensemaking I: Alternative Perspectives,” IEEE Intelligent Systems, 21(4), Jul/Aug 2006, pp. 70-73.

 

If there is additional time we want to venture into some recent technical articles and a blog.  We want to revisit the Deep Mind article on Deep Reinforcement Learning.  arXiv:1312.5602v1 [cs.LG] 19 Dec 2013.  Playing Atari with Deep Reinforcement Learning:

 

Abstract:  We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.

 

On that same topic there is a useful blog:

 

http://www.nervanasys.com/demystifying-deep-reinforcement-learning/

 

Guest Post (Part I): Demystifying Deep Reinforcement Learning

Two years ago, a small company in London called DeepMind uploaded their pioneering paper “Playing Atari with Deep Reinforcement Learning” to Arxiv. In this paper they demonstrated how a computer learned to play Atari 2600 video games by observing just the screen pixels and receiving a reward when the game score increased. The result was remarkable, because the games and the goals in every game were very different and designed to be challenging for humans. The same model architecture, without any change, was used to learn seven different games, and in three of them the algorithm performed even better than a human!

It has been hailed since then as the first step towards general artificial intelligence – an AI that can survive in a variety of environments, instead of being confined to strict realms such as playing chess. No wonder DeepMind was immediately bought by Google and has been on the forefront of deep learning research ever since. In February 2015 their paper “Human-level control through deep reinforcement learning” was featured on the cover of Nature, one of the most prestigious journals in science. In this paper they applied the same model to 49 different games and achieved superhuman performance in half of them.

Still, while deep models for supervised and unsupervised learning have seen widespread adoption in the community, deep reinforcement learning has remained a bit of a mystery. In this blog post I will be trying to demystify this technique and understand the rationale behind it. The intended audience is someone who already has background in machine learning and possibly in neural networks, but hasn’t had time to delve into reinforcement learning yet.

news summary (40)

Categories: Uncategorized

Weekly QuEST Discussion Topics and News, 15 Jan

January 14, 2016 Leave a comment

QuEST 15 Jan 2016:

We will continue this week with the material from the Kabrisky Memorial Lecture for 2016: ‘What is QuEST?’  As all QuEST meetings this will be an interactive discussion of the material so anyone who has never been exposed to our effort can catch up and those who have been involved can refine their personal views on what we seek – last week we got to the dual process model part of the discussion – we will pick up there – there was also some new discussion on the theoretical framework (math) so we’ve inserted a new slide there and our colleague Robert P also gave us some new summary slides on intuitive cognition that we’ve inserted – the new slides will be posted for those inside the fence – for those outside the fence please let us know if you want the slides.

QuEST – Qualia Exploitation of Sensing Technology – a Cognitive exoskeleton

PURPOSE

 

– QuEST is an innovative analytical and software development approach to improve human-machine team decision quality over a wide range of stimuli (handling unexpected queries) by providing computer-based decision aids that are engineered to provide both intuitive reasoning and “conscious” deliberative thinking.

 

– QuEST provides a mathematical framework to understand what can be known by a group of people and their computer-based decision aids about situations to facilitate prediction of when more people (different training) or computer aids are necessary to make a particular decision.

 

 

DISCUSSION

 

– QuEST defines a new set of processes that will be implemented in computer agents.

 

– Decision quality is dominated by the appropriate level of situation awareness.  Situation awareness is the perception of environmental elements with respect to time/space, logical connection, comprehension of their meaning, and the projection of their future status.

 

– QuEST is an approach to situation assessment (processes that are used to achieve situation awareness) and situation understanding (comprehension of the meaning of the information) integrated with each other and the decision maker’s goals.

 

– QuEST solutions help humans understand the “so what” of the data {sensemaking ~ “a motivated, continuous effort to understand connections (among people, places and events) in order to anticipate their trajectories and act effectively” for decision quality performance}.1

 

– QuEST agents implement blended dual process cognitive models (have both artificial conscious and artificial subconscious/intuition processes) for situation assessment.

 

— Artificial conscious processes implement in working memory the QuEST Theory of Consciousness (structural coherence, situation based, simulation/cognitively decoupled).

 

— Subconscious/intuition processes do not use working memory and are thus considered autonomous (do not require consciousness to act) – current approaches to data driven, artificial intelligence provide a wide range of options for implementing instantiations of capturing experiential knowledge used by these processes.

 

– QuEST is developing a ‘Theory of Knowledge’ to provide the theoretical foundations to understand what an agent or group of agents can know, which fundamentally changes human-computer decision making from an empirical effort to a scientific effort.

 

1 Klein, G., Moon, B. and Hoffman, R.R., “Making Sense of Sensemaking I: Alternative Perspectives,” IEEE Intelligent Systems, 21(4), Jul/Aug 2006, pp. 70-73.

 

news summary (39)

Categories: Uncategorized

Kabrisky Memorial Lecture – QuEST 8 Jan

January 7, 2016 Leave a comment

QuEST 8 Jan 2016:

The Kabrisky Memorial Lecture for 2016: ‘What is QuEST?’  The first QuEST meeting of each calendar year we give the Kabrisky Memorial Lecture (in honor of our late colleague Prof Matthew Kabrisky) that brings together our best ‘What is QuEST’ information.  As all QuEST meetings this will be an interactive discussion of the material so anyone who has never been exposed to our effort can catch up and those who have been involved can refine their personal views on what we seek.

QuEST – Qualia Exploitation of Sensing Technology – a Cognitive exoskeleton

PURPOSE

 

– QuEST is an innovative analytical and software development approach to improve human-machine team decision quality over a wide range of stimuli (handling unexpected queries) by providing computer-based decision aids that are engineered to provide both intuitive reasoning and “conscious” deliberative thinking.

 

– QuEST provides a mathematical framework to understand what can be known by a group of people and their computer-based decision aids about situations to facilitate prediction of when more people (different training) or computer aids are necessary to make a particular decision.

 

 

DISCUSSION

 

– QuEST defines a new set of processes that will be implemented in computer agents.

 

– Decision quality is dominated by the appropriate level of situation awareness.  Situation awareness is the perception of environmental elements with respect to time/space, logical connection, comprehension of their meaning, and the projection of their future status.

 

– QuEST is an approach to situation assessment (processes that are used to achieve situation awareness) and situation understanding (comprehension of the meaning of the information) integrated with each other and the decision maker’s goals.

 

– QuEST solutions help humans understand the “so what” of the data {sensemaking ~ “a motivated, continuous effort to understand connections (among people, places and events) in order to anticipate their trajectories and act effectively” for decision quality performance}.1

 

– QuEST agents implement blended dual process cognitive models (have both artificial conscious and artificial subconscious/intuition processes) for situation assessment.

 

— Artificial conscious processes implement in working memory the QuEST Theory of Consciousness (structural coherence, situation based, simulation/cognitively decoupled).

 

— Subconscious/intuition processes do not use working memory and are thus considered autonomous (do not require consciousness to act) – current approaches to data driven, artificial intelligence provide a wide range of options for implementing instantiations of capturing experiential knowledge used by these processes.

 

– QuEST is developing a ‘Theory of Knowledge’ to provide the theoretical foundations to understand what an agent or group of agents can know, which fundamentally changes human-computer decision making from an empirical effort to a scientific effort.

 

1 Klein, G., Moon, B. and Hoffman, R.R., “Making Sense of Sensemaking I: Alternative Perspectives,” IEEE Intelligent Systems, 21(4), Jul/Aug 2006, pp. 70-73.

 

news summary (37)

Categories: Uncategorized