CCSI 5922 Neural Networks and Deep Learning: Introduction 1

Slides:

Advertisements

Similar presentations

Personalizing Education With Machine Learning Workshop Organizers Mike Mozer, Rob Lindsey University of Colorado, Boulder Javier Movellan, Jake Whitehill.

Advertisements

Artificial Neural Networks (1)

CSC321: 2011 Introduction to Neural Networks and Machine Learning Lecture 7: Learning in recurrent networks Geoffrey Hinton.

Template design only ©copyright 2008 Ohio UniversityMedia Production Spring Quarter  A hierarchical neural network structure for text learning.

Tuomas Sandholm Carnegie Mellon University Computer Science Department

Machine Learning for Information Retrieval: Neural Networks, Symbolic Learning, and Genetic Algorithms Prerak Sanghvi Paper by: Hsinchun Chen Artificial.

1 Hybrid Agent-Based Modeling: Architectures,Analyses and Applications (Stage One) Li, Hailin.

1 McGraw-Hill/Irwin Copyright © 2004, The McGraw-Hill Companies, Inc. All rights reserved. Chapter 8: Decision Support Systems Decision Support in Business.

Vedrana Vidulin Jožef Stefan Institute, Ljubljana, Slovenia

Machine Learning CS 165B Spring 2012

CSCI 347 – Data Mining Lecture 01 – Course Overview.

1 TOPIC 1 INTRODUCTION TO COMPUTER SCIENCE AND PROGRAMMING Topic 1 Introduction to Computer Science and Programming Notes adapted from Introduction to.

Adapting Convergent Scheduling Using Machine Learning Diego Puppin*, Mark Stephenson †, Una-May O’Reilly †, Martin Martin †, and Saman Amarasinghe † *

Artificial Intelligence: Prospects for the 21 st Century Henry Kautz Department of Computer Science University of Rochester.

From Machine Learning to Deep Learning. Topics that I will Cover (subject to some minor adjustment) Week 2: Introduction to Deep Learning Week 3: Logistic.

Machine Learning Using Support Vector Machines (Paper Review) Presented to: Prof. Dr. Mohamed Batouche Prepared By: Asma B. Al-Saleh Amani A. Al-Ajlan.

Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Lecture 9 of 42 Wednesday, 14.

Chapter 4 Decision Support System & Artificial Intelligence.

ICS 586: Neural Networks Dr. Lahouari Ghouti Information & Computer Science Department.

Kaifeng Chen Institute for Theoretical Physics Synthetic Biology with Engineering Tools 1 Francis Chen.

Exploiting Cognitive Constraints To Improve Machine-Learning Memory Models Michael C. Mozer Department of Computer Science University of Colorado, Boulder.

Chapter 1: Introduction to Neuro-Fuzzy (NF) and Soft Computing (SC)

1 Software Test Computer Science Department, Information Faculty Dr. KaiYu Wan.

Three challenges for computational models of cognition

Vedrana Vidulin Jožef Stefan Institute, Ljubljana, Slovenia

Convolutional LSTM Networks for Subcellular Localization of Proteins

COSC 4426 AJ Boulay Julia Johnson Artificial Neural Networks: Introduction to Soft Computing (Textbook)

Discovering Optimal Training Policies: A New Experimental Paradigm Robert V. Lindsey, Michael C. Mozer Institute of Cognitive Science Department of Computer.

Community Event Twanna Bradford Professor Williams Final Project June 5, 2016.

Chapter 13 Artificial Intelligence. Artificial Intelligence – Figure 13.1 The Turing Test.

Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation EMNLP’14 paper by Kyunghyun Cho, et al.

Attention Model in NLP Jichuan ZENG.

Deep Learning: What is it good for? R. Burgmann

Preparing for the Cognitive Generation of Decision Support

Hierarchical Question-Image Co-Attention for Visual Question Answering

CS 4501: Introduction to Computer Vision Computer Vision + Natural Language Connelly Barnes Some slides from Fei-Fei Li / Andrej Karpathy / Justin Johnson.

CSE 190 Neural Networks: How to train a network to look and see

New Machine Learning in Medical Imaging Journal Club

INFORMATION COMPRESSION, MULTIPLE ALIGNMENT, AND INTELLIGENCE

Table 1. Advantages and Disadvantages of Traditional DM/ML Methods

Matt Gormley Lecture 16 October 24, 2016

RESEARCH APPROACH.

SMA5422: Special Topics in Biotechnology

Artificial Intelligence and Society

Spring Courses CSCI 5922 – Probabilistic Models (Mozer) CSCI Mind Reading Machines (Sidney D’Mello) CSCI 7000 – Human Centered Machine Learning.

CSCI 5922 Neural Networks and Deep Learning: NIPS Highlights

Shunyuan Zhang Nikhil Malik

Deep Learning Workshop

CSCI 5822 Probabilistic Models of Human and Machine Learning

Hybrid computing using a neural network with dynamic external memory

Project Implementation for ITCS4122

CSCI 5822 Probabilistic Models of Human and Machine Learning

Neural network systems

RNN and LSTM Using MXNet Cyrus M Vahid, Principal Solutions Architect

Connectionist Knowledge Representation and Reasoning

Incremental Training of Deep Convolutional Neural Networks

Turn Key Adaptive Learning Solutions

The use of Neural Networks to schedule flow-shop with dynamic job arrival ‘A Multi-Neural Network Learning for lot Sizing and Sequencing on a Flow-Shop’

Neural Networks Geoff Hulten.

Lecture 02: Perceptron By: Nur Uddin, Ph.D.

2004: Topics Covered in COSC 6368

Lecture 4. Niching and Speciation (1)

EE 193: Parallel Computing

CIS 519 Recitation 11/15/18.

CSCE156: Introduction to Computer Science II

Neural Machine Translation using CNN

A Neural Network for Car-Passenger matching in Ride Hailing Services.

CRCV REU 2019 Aaron Honculada.

Presentation transcript:

CCSI 5922 Neural Networks and Deep Learning: Introduction 1 Mike Mozer Department of Computer Science and Institute of Cognitive Science University of Colorado at Boulder position audience

Mozer (1987) thesis: not much more to be done with convolutional nets!

Mozer (1992) Units with a 1-1 linear self connection Juergen / Sepp as postdocs -> added some gates -> LSTM ‘that’s an ugly architecture’

Mozer et al. (1995) Adaptive House

Current Research Interests Human optimization developing software tools to improve how people learn, remember, make decisions Cognitively informed machine learning developing machine learning algorithms that leverage insights from human perception and cognition Two interrelated threads… I’ll talk about some of this work during my lectures, but let me give you a few other examples to give you the flavor

Human-Machine Cooperative Visual Search (Kneusel & Mozer, 2017) Hard Highlighting Soft Highlighting population d’ human 2.23 classifier 2.28 human + hard highlights 2.64 human + soft highlights 2.80 Challenging visual search problems where people are imperfect but machines aren’t yet to the level of people

Rating Decontamination (Wilder, Jones, & Mozer, in preparation) 1 neither bad nor wrong 10 extremely evil Sequential dependencies in ratings movies, homework grades, length of a line Given contamination introduced by sequential dependencies, we can train models to decontaminate sequences obtains 5-25% improvement in quality of human judgments testifying falsely for pay stealing a hotel towel shooting striking workers yelling at a slow driver poisoning a barking dog poisoning a barking dog

Personalized Review For Promoting Long-Term Retention (Lindsey, Shroyer, Pashler, & Mozer, 2014) 12.4% 16.5%

Training Humans To Categorize (Roads & Mozer, 2017) Belted Kingfisher Ringed Kingfisher Melanoma Benign Ironic Not Ironic Compost Paper psychologists study these dopey artificial stimuli Tim Rogers – words and concepts Karen Schloss

Concept Learning Experiment Hal Pashler UC San Diego

Recurrent Neural Net: Generic Model of Domain-Independent Human Learning? (Roads & Mozer, 2017) AUC