Time Table Time 10 September 11 September 12 September 13 ...

randombroadΤεχνίτη Νοημοσύνη και Ρομποτική

15 Οκτ 2013 (πριν από 4 χρόνια και 2 μήνες)

88 εμφανίσεις

Time Table

Time

10 September

11 September

12 September

13 September

8:30
-
9:30

Registration

Registration

Registration

Registration

9
:
30
-
1
0:3
0

Key Lecture 1

Nikola Kasabov

Key Lecture 3

Steven
Grossberg

Key Lecture 5

Alessandro Villa

Session

11

Session

1
2

11
:
00
-
11
:
30

Coffee Break

Coffee Break

Coffee Break

Coffee Break

11:
30
-
13
:
00

Session

1

Session

2

Session 5

Session

6

Session

7

Session

8

Tuturial
2

Alexander Gegov

13
:
30
-
14
:
30

Lunch time

Lunch time

Lunch time

Conference closing

14:30
-
15:30

Key Lecture
2

Er
k
ki Oja

Key Lecture 4

Karlheiz Meier

Key Lecture 6

Gu
e
nther Palm


1
5:
30
-
1
7:
0
0

Session 3

Session

4

Tutorial 1

Bruno Apoloni

&
Simone Bassis

Session 9

Session

10


1
7:
0
0
-
1
7
:
3
0

Coffee Break

Coffee Break

Coffee Break


17
:
3
0
-
18
:3
0

Poster

Session

1

Poster

Session 2

Elections &

ENNS board
meeting


21
:
00
-
23
:
00

Welcome

Cocktail


Gala

Dinner




Program

Session 1:
Neural network theory & Models I

015

Model
-
based clustering of temporal data

023

Fast approximation method for Gaussian process regression using
hash function for non
-
uniformly distributed data

026

An Analytical Approach to Delay
-
Coupled Reservoir Computing

034

Applying general
-
purpose Data Reduction Techniques for fast time series classification


Session 2: Pattern recognition & Classification
I

006

Feature Weighting by Maximum Distance Minimization

049

Training Computationally Efficient Smartphone
-
Based Human Activity Recognition
Models

052

A General Image Representation Scheme and its Improvement for Image Analysis


Session
3
: Brain
-
machine

interactions & Bio
-
inspired systems

056

Unsupervised online calibration of a c
-
VEP Brain
-
Computer Interface (BCI)

057

A Biologically Inspired Model for the Detection of External and Internal Head Motions

035

Embodied Language Understanding with a Multip
le Timescale Recurrent Neural
Network

122

Learning Sensorimotor Transformations with Dynamic Neural Fields


Session 4: Pattern recognition & Classification II

070

Online Classification of Eye Tracking Data for Automated Analysis of Traffic Hazard
Perception

073

Handwritten Digit Recognition with Pattern Transformations and Neural Network
Averaging

075

Hearing aid classification based on audiology data

085

BLSTM
-
RN
N based 3D Gesture Classification



Session
5
: Neural network theory & Models II

039

Two
-
layer vector perceptron

043

Local Detection of Communities by Neural
-
Network Dynamics

067

The Super
-
Turing Computational Power of Interactive Evolving Recurrent Neu
ral
Networks

087

Group Fused Lasso

130

GNMF with Newton
-
based Methods


Session 6: Neural network applications in Robotics and Control

003

Adaptive Critic Neural Network Solution of Optimal Control Problems with Delays in State and
Control Variables

110

A Software Framework for Cognition, Embodiment, Dynamics, and Autonomy in Robotics:
cedar

112

Real
-
Time Interface Board for Closed
-
Loop Robotic Tasks on the SpiNNaker Neural
Computing System

068

Time
-
series forecasting of indoor temperature using pre
-
tr
ained Deep Neural Networks


Session
7
: Cognitive science & Neuroscience I

010

Attention
-
Gated Reinforcement Learning in Neural Networks
-
A Unified View

099

Evolution of Dendritic Morphologies using Deterministic and Nondeterministic Genotype to
Phenotype
Mapping

041

Learning Temporally Precise Spiking Patterns through Reward Modulated Spike
-
Timing
-
Dependent Plasticity

053

Robust Principal Component Analysis for Brain Imaging


Session 8: Machine learning & Learning algorithms I

047

Learning of Lateral In
teractions for Perceptual Grouping employing Information Gain

059

On
-
line Laplacian One
-
Class Support Vector Machines

072

Learning with hard constraints

132

Novel feature selection and kernel
-
based value approximation method for reinforcement
learning

140

OSA: One
-
class Recursive SVM Algorithm with Negative Samples for Fault Detection


Session
9
: Cognitive science & Neuroscience II

058

Phase Control of Coupled Neuron Oscillators

004

Memory trace in spiking neural networks

101

Sparseness Controls the
Receptive Field Characteristics of V4 Neurons: Generation of
Curvature Selectivity in V4


Session
10
: Machine learning & Learning algorithms II

001

A Two
-
Stage Pretraining Algorithm for Deep Boltzmann Machines

012

A Low
-
Energy Implementation of Finite Au
tomata by Optimal
-
Size Neural Nets

027

Efficient Baseline
-
free Sampling in Parameter Exploring Policy Gradients: Super Symmetric
PGPE

028

Direct Method for Training Feed
-
forward Neural Networks using Batch Extended Kalman Filter
for Multi
-
Step
-
Ahead Pred
ictions

024

Improving the Associative Rule Chaining Architecture


Session 11: Pattern recognition & Classification III

090

Feature Selection for Neural Network
-
Based Interval Forecasting of Electricity Demand Data

106

A Combination of Hand
-
crafted and H
ierarchical High
-
level Learnt Feature Extraction for
Music Genre Classification

123

An Effective Dynamic Gesture Recognition System based on the Feature Vector Reduction for
SURF and LCS

046

Using the Analytic Feature Framework for the Detection of Occlud
ed Objects


Session 12: Other applications of neural networks

029

Wind Power Resource Estimation with Deep Neural Networks

048

Wavelet Neural Networks for Electricity Load Forecasting


Dealing with Border Distortion and
Shift Invariance

071

An Echo Sta
te Network with Working Memories for Probabilistic Language Modeling

066

Learning Features for Activity Recognition with Shift
-
invariant Sparse Coding


Poster session 1:

032

Emotion Generation System considering Complex Emotion based on MaC Model with Ne
ural
Networks

133

Balancing of a Simulated Inverted Pendulum Using the NeuraBASE Network Model

025

The Imbalance Network and Incremental Evolution for Mobile Robot Nervous System Design

077

Neuro
-
Optimal Controller for Robot Manipulators

120

Learning t
o walk using a Recurrent neural network with time delay

086


Recurrent Fuzzy
-
Neural Network with fast learning algorithm for Predictive Control

017

EEG Dataset Reduction and Classification Using Wave Atom Transform

119

Cortically Inspired Sensor Fusion

Network for Mobile Robot Heading Estimation

036

Dynamic Memory for Robot Control using Delay
-
based Coincidence Detection Neurones

074

Dendritic computations in a Rall model with strong distal stimulation

089

Modeling Action Verb Semantics Using Motion
Tracking

060

Boltzmann Machines for Image Denoising

136

Vehicle plate recognition using improved neocognitron neural network

030

Comparison on Late Fusion Methods of Low Level Features for Content Based Image Retrieval


Poster session 2:

016

A Distribu
ted Learning Algorithm Based on Frontier Vector Quantization and Information Theory

079

Bidirectional Activation
-
based Neural Network Learning Algorithm

081

A Neural Network Model for Online Multi
-
task Multi
-
Label Pattern Recognition

116

Exponential syn
chronization of a class of RNNs with discrete and distributed delays

126

Variational Foundations of Online Backpropagation

009

Hessian Corrected Input Noise Models

069

Optimal Operation of Electric Power Production System without Transmission Losses u
sing
Artificial Neural Networks based on Augmented Lagrange Multiplier Method

007

Using Exponential Kernel for Word Sense Disambiguation

065

Interactive Two
-
Level WEBSOM for Organizational Exploration

008

Independent Component Analysis filtration for Va
lue at Risk modelling

121

Echo State Networks in Dynamic Data Clustering

037

Self
-
Organization in Parallel Coordinates

050

A Novel Procedure for Training L1
-
L2 Support Vector Machine Classifiers

114

Coordinated Rule Acquisition of Decision Making on Su
pply Chain by Exploitation
-
oriented
Reinforcement Learning
-
Beer Game as an Example
-

115

Exploration of loneliness questionnaires using the self
-
organising map



Tutorial 1:

Title
:

Algorithmic Inference, a statistical framework in the Machine Learning e
poch

Tutors:

Bruno Apolloni
a
nd Simone Bass
is, University of Milano, Italy


We revise the basic estimation instances of the parameters occurring in the machine learning
framework in terms of their compatibility with the sample we have observed. This is a r
ecent
perspective that allows us to get a more intuitive feeling of the crucial concept of the confidence
interval. The key artifact consists of working with a representation of the compatible parameters
in terms of random variables without priors. We supp
ort our methods with: a consistent
theoretical framework,

general
-
purpose estimation procedures, and a set of paradigmatic
benchmarks.



Tutorial 2:

Title:
Rule Based Network Models for Complex Systems

Tutor:
Alexander Gegov,
University of Portsmouth, UK


This tutorial consists of 10 sections. The first section discusses complexity as a systemic feature
and the ability of rule based systems to handle different attributes of complexity. Section 2
reviews several types of rule based systems in the context of
systemic complexity, including
systems with single, multiple and networked rule bases. Section 3 introduces rule based network
models for complex systems such as Boolean matrices, binary relations, block schemes and
topological expressions. Section 4 prese
nts basic operations on nodes in rule based networks,
including merging and splitting in horizontal, vertical and output context. Section 5 discusses
structural properties of basic operations such as associativity of merging and variability of
splitting in

horizontal, vertical and output context. Section 6 describes advanced operations on
nodes in rule based networks, including node transformation for input augmentation, output
permutation and feedback equivalence, as well as node identification in horizont
al, vertical and
output merging. Section 7 shows the application of the theoretical results from Sections 3
-
6 in
feedforward rule based networks with single or multiple levels and layers. Section 8 illustrates
the application of the theoretical results fro
m Sections 3
-
6 in feedback rule based networks with
single or multiple local and global feedback. Section 9 evaluates rule based networks in the
context of fuzzy logic by means of composition of hierarchical fuzzy systems, decomposition of
standard fuzzy s
ystems, indicators of model performance and applications for case studies. The
last section highlights the theoretical significance, the application areas and the methodological
impact of the presented rule based network models for complex systems. More de
tails about this
tutorial can be found at:

http://www.springer.com/engineering/computational+intelligence+and+comp
lexity/book/978
-
3
-
642
-
15599
-
4



Exhibition:
FP7 European Project "SOCIAL&
SMART"

Presenters:
Bruno Apolloni
a
nd
Gian Luca Galliani
, University of Milano, Italy


During the conference a demo of the

FP7 European Project "SOCIAL&
SMART" be presented.
The demo
will consist of

a remote control of a domestic system, where a washing machine
located in the Milano lab is operated in all its details (such as drum r.p.m. and soak duration)
from
a

laptop in Sofia. A serious game on the system will be uploadable by the v
isitors.