cognitive computing by professor gordon pipa
TRANSCRIPT
Institute of Cognitive ScienceCognitive Computing
Prof. Dr. Gordon Pipa
Chair of the Neuroinformatics Department
Institute of Cognitive Science
Osnabrück University
Institute of Cognitive Science
The Science of Our Minds
By Philip Erpenbeck - Motion Designer
Institute of Cognitive Science
At the Core of Cognitive Computing since 15 Years
Technology
Interaction
Humans
Artificial Intelligence
Neurolinguistics
Cognitive Modelling
Neurobiopsychology
Cognitive Robotics
Neuroinformatics
NeuroinspiredComputer Vision
Computational Linguistics
Cognitive PsychologyPhilosophy of Mind
10 Full professors
~ 600 BSc~ 200 MSc ~ 45 PhD students
Institute of Cognitive Science
Influenza
matters
Prediction is
important
Delayed and
too few data
Why Cognitive Computing?
A one year project by a core team of three master’s students
Institute of Cognitive Science
Influenza
matters
Prediction is
important
Delayed and
too few data
Why Cognitive Computing?
Social media
analysis
Data science
methods
Watson as
medical expert
Institute of Cognitive Science
Influenza
matters
Prediction is
important
Delayed and
too few data
Why Cognitive Computing?
Social media
analysis
Data science
methods
Watson as
medical expert
Fully informed
user
Better
prediction
Cognitive Computing
Institute of Cognitive Science
Influenza
matters
Prediction is
important
Delayed and
too few data
Why Cognitive Computing?
Social media
analysis
Data science
methods
Watson as
medical expert
Fully informed
user
Better
prediction
Institute of Cognitive Science
Structured Causal Models
• Disease spreads locally and via transportation hubs• Weather, vaccination, and seasonal events change spreading
Institute of Cognitive Science
Structured Causal Models
• Disease spreads locally and via transportation hubs• Weather, vaccination, and seasonal events change spreading
Institute of Cognitive Science
Structured Causal Models
• Disease spreads locally and via transportation hubs• Weather, vaccination, and seasonal events change spreading
Institute of Cognitive Science
Structured Causal Models
Direction and speed of spread NEEDS to be identified from data
Institute of Cognitive Science
Identify Causal Interactions
A driver influences andthereby leaves a trace that can be reconstructed
B
• Schumacher et al. (2015) - A Statistical Framework to Infer Delay and Direction of Information …• Sugihara et al. (2012) - Detecting Causality in Complex Ecosystems
AC
Institute of Cognitive Science
Identify Causal Interactions
The model can be analyzed:When is New York going to be hit?
• Schumacher et al. (2015) - A Statistical Framework to Infer Delay and Direction of Information …• Sugihara et al. (2012) - Detecting Causality in Complex Ecosystems
BA
C
Institute of Cognitive Science
Identify Causal Interactions
The model can be analyzed:Can vaccinations in Chicago stop the wave?
• Schumacher et al. (2015) - A Statistical Framework to Infer Delay and Direction of Information …• Sugihara et al. (2012) - Detecting Causality in Complex Ecosystems
BA
C
Institute of Cognitive Science
IBM Blue Mix & Watson at work
Supported by:
Institute of Cognitive Science
IBM Blue Mix & Watson at work
Supported by:
Institute of Cognitive Science
Influenza
matters
Prediction is
important
Delayed and
too few data
Why Cognitive Computing?
Social media
analysis
Data science
methods
Watson as
medical expert
Fully informed
user
Better
prediction
Institute of Cognitive Science
Social Media
Twitter gives realtime and anytime available data IBM Insights contains tweets since 2014
Twitter activity (geo tag + tweet)
Institute of Cognitive Science
Close the Gap by Fusing Data
Realtime fuzzy social media
+ Slow but relibale CDC data
Twitter activity (geo tag + tweet)
CDC – delayed influenca data
Use the best from both worlds to improve prediction
Institute of Cognitive Science
IBM Blue Mix & Watson at Work
Supported by:
Institute of Cognitive Science
IBM Blue Mix & Watson at Work
Supported by:
Institute of Cognitive Science
Influenza
matters
Prediction is
important
Delayed and
too few data
Why Cognitive Computing?
Social media
analysis
Data science
methods
Watson as
medical expert
Fully informed
user
Better
prediction
Institute of Cognitive Science
Why Cognitive Computing?
...
????
Institute of Cognitive Science
Watson at Work
Supported by:
Institute of Cognitive Science
Watson at Work
Supported by:
Institute of Cognitive Science
Summary
Social media
analysis
Data science
methods
Watson as expert
● Data science allows identification of very complex causal relations
● Efficient use of BLUE Mix and Watson services
● Combine social media with other conventional data to get the best of both worlds realtime and reliable
● Use large corpora to identify structure and relationships in your problem
● Use natural language interface for easy to use HCI
Institute of Cognitive Science
Try It Yourself
www.flu-prediction.com
Institute of Cognitive ScienceNEUROMORPHIC COMPUTING
• Neuronal plasticity for local learning
• Delays as a feature to rendercomputation more efficent
• Spatiotemporal computations of an excitable and plastic brain: neuronal plasticity leads to noise-robust and noise-constructive computations, H. Toutounji, G. Pipa - PLOS Comput Biol, 2014
• An introduction to delay-coupled reservoir computing, J. Schumacher, H. Toutounji, G. Pipa, Artificial Neural Networks, Vol 4, Springer Series in Bio-/Neuroinformatics pp 63-90
Linear task
specific
mapping
Echo State Networks ESN (Jager, 2002)Liquid State Machines LSM (Maass et al 2003)
Institute of Cognitive ScienceNEUROMORPHIC COMPUTING
• Unsupervised Representation learning based on neuronal plasticity (IP + STDP )
Here higher order markov transitions
• Spatiotemporal computations of an excitable and plastic brain: neuronal plasticity leads to noise-robust and noise-constructive computations, H. Toutounji, G. Pipa; PLOS Computational Biology, 2014
• SORN: a self-organizing recurrent neural network, Frontiers in computational neuroscience 3, 23
Institute of Cognitive ScienceNEUROMORPHIC COMPUTING
• An introduction to delay-coupled reservoir computing, J. Schumacher, H. Toutounji, G. Pipa, Artificial Neural Networks, Vol 4, Springer Series in Bio-/Neuroinformatics pp 63-90
• ‘Neuromorphic computation in multi-delay coupled models’, P. Nieters, J. Leugering, G. Pipa, IBM Research Journals (submitted)
Recurrent network reservoir Delay coupled reservoir
Institute of Cognitive ScienceLEARNING TO FLY – LIKE A BIRD
• Bioinspired motor control
• Use of real-time recurrentnetworks
• Reservoir computing systemlearns complex flightdynamics
Institute of Cognitive ScienceNEURO-INSPIRED SYSTEMS
Spatiotemporal computations of an excitable and plastic brain: neuronal plasticity leads to noise-robust and noise-constructive computations, H. Toutounji, G. Pipa - PLOS Comput Biol, 2014
Linear mappingReservoirInput
Current Position
Current Yaw
Current Pitch
Current Roll
Target Position
Institute of Cognitive Science
Neuro-Inspired Self-Learning Systems
Institute of Cognitive Science
Mobile Crowd EEG
• Less than $99, 8 channel,
LED stimulation, gyroscope
• Mobile system with Bluetooth LE
• Allows for nothing less than a new ERA of crowd EEG experiments
Institute of Cognitive Science
The Future of ALP Crowd Bio-Signals
You design your analysis that we perform for you.
Pay for the service and the data you get.
We store and process the data.
We rent
devices.
Institute of Cognitive Science
The Cognitive ERA
JOIN THE ADVENTURE
LEARN HOW TO USE THE POWER OF THE BRAIN
Supported by:
Prof. Dr. Gordon [email protected]
Osnabrück University
Institute of Cognitive Science
The Moral/Ethical Turing Test
“When the light turned green, the Google car waited for a few cars to pass and then
began moving back into the middle of the lane to pass the sand bags.
At the same time, a public transit bus was approaching from behind.
The Google car expected the bus to stop or slow down to let it into the traffic flow.
That didn't happen. Instead, the self-driving vehicle hit the side of the bus as it was
moving back into the middle of the lane.”
Institute of Cognitive Science
The Moral/Ethical Turing Test
Naturalistic Condition
Skulmowski A, Bunge A, Kaspar K and Pipa G (2014) Forced-choice decision-making in modified trolley dilemmasituations: a virtual reality and eye tracking study. Front. Behav. Neurosci. 8:426. doi: 10.3389/fnbeh.2014.00426
Institute of Cognitive Science
The Moral/Ethical Turing Test
Study project: Moral decisions in the interaction of humans and a car driving assistant
Abstract Condition
Institute of Cognitive Science
The Moral/Ethical Turing Test
Accepted behavior?
Context dependence?
Wish to interfere?
Learning underlying rules
Study project: Moral decisions in the interaction of humans and a car driving assistant
Institute of Cognitive Science
Value of Life
Naturalistic (embodied, situated) moral/ethical decisions are more reliable and distinguished than abstract ones