from graphs to neural networks complexity and simplicity
play

From graphs to neural networks: complexity and simplicity in the - PowerPoint PPT Presentation

Sep 27, 2023 •146 likes •391 views

From graphs to neural networks: complexity and simplicity in the framework of mathema9cs Martha-Ivon Crdenas Ar8ficial intelligence research group: So? Compu8ng SOCO. UPC Systems Pharmacology and Bioinforma8cs group. Ins8tut de Neurocincies.

  1. From graphs to neural networks: complexity and simplicity in the framework of mathema9cs Martha-Ivon Cárdenas Ar8ficial intelligence research group: So? Compu8ng SOCO. UPC Systems Pharmacology and Bioinforma8cs group. Ins8tut de Neurociències. UAB mcardenas@cs.upc.edu

  2. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Learning from Graphs: pa<ern recogni9on To bridge AI with pa<ern modelling in secondary/high school To introduce the concept of computa9onal sciences Not only sta9s9cs data but also rela9onal data STEAM methodology can help us with this task

  3. Graphs in a nutshell Simplicity Powerful analysis Not only about geometry Visualiza9on of interacions Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020)

  4. Graphs in a nutshell Simplicity Powerful analysis Not only about geometry Visualiza9on of interacions Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020)

  5. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020)

  6. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Networks: airplains in Europe

  7. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Networks: Facebook

  8. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) y = mx + b Neuron Linear perceptron

  9. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) y = mx + b Neuron Linear perceptron - activation function

  10. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) y = mx + b Neurons Connected linear perceptrons

  11. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Connected linear perceptrons Neural network

  12. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Graph Adjacency Laplacian Degree matrix matrix matrix

  13. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Learning Giving math sense to neural networks

  14. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Classification Clustering Rules

  15. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Decoding the meaning of the data Minimize the error: backpropaga8on

  16. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Decoding the meaning of the data Minimize the error: backpropaga8on

  17. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020)

  18. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020)

  19. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) 2D visualiza9on

  20. cytoscape.org

  21. Zometool

  22. Funny classifica9on

  23. Martha-Ivon Cárdenas: From graphs to neural networks: complexity and simplicity in the framework of mathema8cs (AI4ME 2020) Thank you mcardenas@cs.upc.edu

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Umut Gcl and Marcel A. J. van Gerven Article overview by Ilya Kuzovkin Computational Neuroscience Seminar University of Tartu

852 views • 63 slides
Complexity and Economics The lowest simplicity you can achieve is the complexity Jo ao Basilio

Complexity and Economics The lowest simplicity you can achieve is the complexity Jo ao Basilio

Complexity and Economics The lowest simplicity you can achieve is the complexity Jo ao Basilio Pereima joaobasilio@ufpr.br Department of Economics Graduate Program in Economic Development Curitiba-Paran a-Brazil 6 de marc o de 2015

480 views • 35 slides
Complexity and Economics The lowest simplicity you can achieve is the complexity Jo ao Basilio

Complexity and Economics The lowest simplicity you can achieve is the complexity Jo ao Basilio

Complexity and Economics The lowest simplicity you can achieve is the complexity Jo ao Basilio Pereima joaobasilio@ufpr.br Department of Economics Graduate Program in Economic Development Curitiba-Paran a-Brazil 13 de junho de 2016

826 views • 55 slides
Simplicity and Complexity of Belief-Propagation Elchanan Mossel 1 1 MIT Dec 2020 Elchanan Mossel

Simplicity and Complexity of Belief-Propagation Elchanan Mossel 1 1 MIT Dec 2020 Elchanan Mossel

Simplicity and Complexity of Belief-Propagation Elchanan Mossel 1 1 MIT Dec 2020 Elchanan Mossel Simplicity &amp; Complexity of BP Markov Random Fields and Information Flow on Trees Consider the following process on a tree. Color the root

454 views • 10 slides
Neural Networks and Computation Graphs CS 6956: Deep Learning for NLP Based on slides and

Neural Networks and Computation Graphs CS 6956: Deep Learning for NLP Based on slides and

Neural Networks and Computation Graphs CS 6956: Deep Learning for NLP Based on slides and material from Geoffrey Hinton, Richard Socher, Yoav Goldberg, and others. The computation graph slides are based on a tutorial Practical Neural

1.5k views • 121 slides
Outline Evolution of neurocomputing Artificial neural networks Feed forward

Outline Evolution of neurocomputing Artificial neural networks Feed forward

Introduction to Neural Networks and Deep Learning Ling Guan References: S. Haykin, Neural Networks , 2 nd Edition, New Jersey: Prentice Hall, 1. 2004. C. M. Bishop, Neural Networks for Pattern Re cognition, New York: 2. Oxford University

451 views • 17 slides
IN5550 Neural Methods in Natural Language Processing Recurrent Neural Networks Stephan Oepen

IN5550 Neural Methods in Natural Language Processing Recurrent Neural Networks Stephan Oepen

IN5550 Neural Methods in Natural Language Processing Recurrent Neural Networks Stephan Oepen University of Oslo March 10, 2019 Our Roadmap Today Language structure: sequences, trees, graphs Recurrent Neural Networks Different

780 views • 76 slides
On The Complexity of Training a Neural Network Santosh Vempala Algorithms and Randomness Center

On The Complexity of Training a Neural Network Santosh Vempala Algorithms and Randomness Center

On The Complexity of Training a Neural Network Santosh Vempala Algorithms and Randomness Center Georgia Tech The Complexity of Learning Neural Networks Deep learning s successes are incredible Do you want to beat 9 dan Goplayers? The

873 views • 55 slides
Simplicity and Complexity of Belief-Propagation Elchanan Mossel 1 1 MIT July 2020 Elchanan Mossel

Simplicity and Complexity of Belief-Propagation Elchanan Mossel 1 1 MIT July 2020 Elchanan Mossel

Simplicity and Complexity of Belief-Propagation Elchanan Mossel 1 1 MIT July 2020 Elchanan Mossel Simplicity &amp; Complexity of BP A Double phase transition for large q Theorem (Count Reconstruction, Robust Reconstruction (Mossel-Peres,

332 views • 17 slides
IN5550 Neural Methods in Natural Language Processing Applications of Recurrent Neural Networks

IN5550 Neural Methods in Natural Language Processing Applications of Recurrent Neural Networks

IN5550 Neural Methods in Natural Language Processing Applications of Recurrent Neural Networks Stephan Oepen University of Oslo March 24, 2019 Our Roadmap Last Week Language structure: sequences, trees, graphs Recurrent Neural

217 views • 19 slides
Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

1.17k views • 91 slides
Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

852 views • 33 slides
Understanding How ConvNets See Springerberg et al, Striving for Simplicity: The All Convolutional

Understanding How ConvNets See Springerberg et al, Striving for Simplicity: The All Convolutional

Understanding How ConvNets See Springerberg et al, Striving for Simplicity: The All Convolutional Net (ICLR 2015 workshops) CSC321: Intro to Machine Learning and Neural Networks, Winter 2016 Slides from Andrej Karpathy Michael Guerzhoy What

248 views • 21 slides
CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks Neuron Non-linearity Softmax layer DNN training Loss function and regularization SGD and backprop Learning rate Overfitting

1.8k views • 86 slides
Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they

1.63k views • 119 slides
Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they

1.57k views • 124 slides
Laser accelerator on a chip in Lund ? Why particle accelerators matter Discovery Science

Laser accelerator on a chip in Lund ? Why particle accelerators matter Discovery Science

Laser accelerator on a chip in Lund ? Why particle accelerators matter Discovery Science Particle accelerators are essential tools of discovery for particle and nuclear physics and for sciences that use x-rays and neutrons. Medicine Tens of

448 views • 16 slides
EE 213, Microscopic Nanocharacterization of Materials Class website:

EE 213, Microscopic Nanocharacterization of Materials Class website:

EE 213, Microscopic Nanocharacterization of Materials Class website: https://ee213-winter16-01.courses.soe.ucsc.edu/ Time/place: Tu/Th 10-11:45am. Baskin 156 Mike Isaacson, Baskin 237 Email: msi@soe.ucsc.edu Tele: 831-459-3190 Admin. Asst.

599 views • 44 slides
Protein-Protein Docking Current Methods and New Challenges Dave Ritchie Team Orpailleur

Protein-Protein Docking Current Methods and New Challenges Dave Ritchie Team Orpailleur

Protein-Protein Docking Current Methods and New Challenges Dave Ritchie Team Orpailleur Inria Nancy Grand Est Outline Review of Selected CAPRI Targets Some Algorithms Used in CAPRI Assembling Symmetric Multimers Hybrid Approaches

628 views • 36 slides
CURRENT CAPABILITIES IN GRATING MANUFACTURING Monday, October 16, 2017 Outline: Bach Research

CURRENT CAPABILITIES IN GRATING MANUFACTURING Monday, October 16, 2017 Outline: Bach Research

Bach Research Corporation CURRENT CAPABILITIES IN GRATING MANUFACTURING Monday, October 16, 2017 Outline: Bach Research Corp. Facilities Recent Projects Capabilities Large Gratings Echelles Grisms

542 views • 15 slides
Solving the Tree Containment Problem for Genetically Stable Networks in Quadratic Time Philippe

Solving the Tree Containment Problem for Genetically Stable Networks in Quadratic Time Philippe

Solving the Tree Containment Problem for Genetically Stable Networks in Quadratic Time Philippe Gambette Andreas D. M. Gunawan Anthony Labarre St ephane Vialette Louxin Zhang International Workshop on Combinatorial Algorithms October 6th,

408 views • 27 slides
MicroVascular Techniques for Limb Salvage Plastic &amp; Reconstructive MicroSurgery

MicroVascular Techniques for Limb Salvage Plastic &amp; Reconstructive MicroSurgery

4/20/2013 MicroVascular Techniques for Limb Salvage Plastic &amp; Reconstructive MicroSurgery Angiosomes Ian Taylor, MD San Francisco (Harry Charles K Lee, MD, FACS Buncke, MD, Stephen Mathes, MD) Chief of Plastic Surgery &amp;

114 views • 10 slides
15 th TF-Mobility Meeting Sensor Networks Torsten Braun Universitt Bern braun@iam.unibe.ch

15 th TF-Mobility Meeting Sensor Networks Torsten Braun Universitt Bern braun@iam.unibe.ch

15 th TF-Mobility Meeting Sensor Networks Torsten Braun Universitt Bern braun@iam.unibe.ch www.iam.unibe.ch/~rvs Torsten Braun: Sensor Networks Overview Zrich, September 28, 2007 2 Torsten Braun: Sensor Networks Ubiquitous Computing

841 views • 24 slides
Artificial Intelligence (IT4042E) Quang Nhat Nguyen quang.nguyennhat@hust.edu.vn Hanoi

Artificial Intelligence (IT4042E) Quang Nhat Nguyen quang.nguyennhat@hust.edu.vn Hanoi

Artificial Intelligence (IT4042E) Quang Nhat Nguyen quang.nguyennhat@hust.edu.vn Hanoi University of Science and Technology School of Information and Communication Technology Academic Year 2020-2021 Content: Introduction of Artificial

862 views • 28 slides

More recommend