Discussion

varunydd2

Sharda_11e_full_accessible_ppt_06.pptx

Home >Computer Science homework help >Discussion

Analytics, Data Science and A I: Systems for Decision Support

Eleventh Edition

Chapter 6

Deep Learning and Cognitive Computing

Slide in this Presentation Contain Hyperlinks. JAWS users should be able to get a list of links by using INSERT+F7

If this PowerPoint presentation contains mathematical equations, you may need to check that your computer has the following installed:

1) Math Type Plugin

2) Math Player (free versions available)

3) NVDA Reader (free versions available)

Learning Objectives (1 of 2)

6.1 Learn what deep learning is and how it is changing the world of computing

6.2 Know the placement of deep learning within the broad family of A I learning methods

6.3 Understand how traditional “shallow” artificial neural networks (A N N) work

6.4 Become familiar with the development and learning processes of A N N

6.5 Develop an understanding of the methods to shed light into the A N N black box

Slide 2 is list of textbook LO numbers and statements

Learning Objectives (2 of 2)

6.6 Know the underlying concept and methods for deep neural networks

6.7 Become familiar with different types of deep learning methods

6.8 Understand how convolutional neural networks (C N N), recurrent neural networks (R N N), and long short-memory networks (L S T M) work

6.9 Become familiar with the computer frameworks for implementing deep learning

6.10 Know the foundational details about cognitive Computing and I B M Watson

Slide 2 is list of textbook LO numbers and statements

Opening Vignette (1 of 4)

Fighting Fraud with Deep Learning and Artificial Intelligence

Business problem

Danske Bank

Predictive analytics in banking

Fraud detection

The solution

Deep learning

The results

Opening Vignette (2 of 4)

Fighting Fraud with Deep Learning and Artificial Intelligence

Accuracy

R O C curve

D L vs traditional M L techniques

Opening Vignette (3 of 4)

Fighting Fraud with Deep Learning and Artificial Intelligence

A Generalized Framework for A I and Deep Learning–Based Analytics Solutions

Opening Vignette (4 of 4)

Discussion Questions:

What is fraud in banking?

What are the types of fraud that banking firms are facing today?

What do you think are the implications of fraud on banks and on their customers?

Compare the old and new methods for identifying and mitigating fraud.

Why do you think deep learning methods provided better prediction accuracy?

Discuss the trade-off between false positive and false negative (type 1 and type 2 errors) within the context of predicting fraudulent activities.

Introduction to Deep Learning (1 of 3)

Imaginative things in the SciFi movies are turning into realities-tanks to A I and Machine Learning

Siri, Google assistant, Alexa, Google home, …

Deep learning is the newest member of the A I/Machine Learning family

Learn better than ever before

The reason for Deep Learning superiority

Automatic feature extraction and representation

Introduction to Deep Learning (2 of 3)

The placement of Deep Learning within the overarching A I-based learning methods

Introduction to Deep Learning (3 of 3)

Differences between Classic Machine-Learning Methods and Representation Learning/Deep Learning

Application Case 6.1 (1 of 2)

Finding the Next Football Star with Artificial Intelligence

Application Case 6.1 (2 of 2)

Finding the Next Football Star with Artificial Intelligence

Discussion Questions:

What does SciSports do? Look at its Web site for more information.

How can advanced analytics help football teams?

What is the role of deep learning in solutions provided by SciSports?

Basics of “Shallow” Learning (1 of 4)

Artificial Neural Networks – abstractions of human brain and its complex biological network of neurons

Neurons = Processing Elements (P E s)

Single-input and single-output neuron/P E

Basics of “Shallow” Learning (2 of 4)

Common transfer (activation) functions

Basics of “Shallow” Learning (3 of 4)

Typical multiple-input neuron with R individual inputs

Basics of “Shallow” Learning (4 of 4)

Typical Neural Network with three layers and eight neurons

Application Case 6.2

Gaming Companies Use Data Analytics to Score Points with Players

Watch: Art of Analytics – The Sword

Discussion Questions:

What are the main challenges for gaming companies?

How can analytics help gaming companies stay competitive?

What types of data can gaming companies obtain and use for analytics?

Technology Insight 6.1 (1 of 3)

Elements of an Artificial Neural Network

Processing element (P E)

Network structure

Hidden layer(s)

Input

Output

Connection weights

Summation function

Transfer function

Technology Insight 6.1 (2 of 3)

Elements of an Artificial Neural Network

Neural Network with One Hidden Layer

Technology Insight 6.1 (3 of 3)

Elements of an Artificial Neural Network

Summation Functions

Transfer Function

Application Case 6.3

Artificial Intelligence Helps Protect Animals from Extinction

Watch: WildTrack

Discussion Questions

What is WildTrack and what does it do?

How can advanced analytics help WildTrack?

What are the roles that deep learning plays in this application case?

Process of Developing Neural-Network Based Systems

A process with constant feedbacks for changes and improvements!

Learning Process in A N N

Compute temporary outputs.

Compare outputs with desired targets.

Adjust the weights and repeat the process.

Backpropagation for A N N Training (1 of 2)

Initialize weights with random values

Read in the input vector and the desired output

Compute the actual output via the calculations

Compute the error.

Change the weights by working backward

Backpropagation for A N N Training (2 of 2)

Illustration of the Overfitting in A N N

Illuminating the Black Box of A N N

A N N are typically known as black boxes

Sensitivity analysis can shed light to the black-box

Application Case 6.4 (1 of 2)

Sensitivity Analysis Reveals Injury Severity Factors in Traffic Accidents

Discussion Questions:

How does sensitivity analysis shed light on the black box (i.e., neural networks)?

Why would someone choose to use a black-box tool such as neural networks over theoretically sound, mostly transparent statistical tools like logistic regression?

In this case, how did neural networks and sensitivity analysis help identify injury-severity factors in traffic accidents?

Application Case 6.4 (2 of 2)

Sensitivity Analysis Reveals Injury Severity Factors in Traffic Accidents

Graphical representation of the sensitivity analysis results for the eight binary A N N model configurations

Deep Neural Networks (1 of 3)

Deep: more hidden layers

In addition to C P U, it also uses G P U

With programming languages like C U D A by N V I D I A

Needs large datasets

Deep learning uses tensors as inputs

Tensor: N-dimensional arrays

Image representation with 3-D tensors

There are different types and capabilities of Deep Neural Networks for different tasks/purposes

Deep Neural Networks (2 of 3)

Feedforward Multilayer Perceptron (M L P)-Type Deep Networks

Most common type of deep networks

Vector Representation of the First Three Layers in a Typical M L P Network.

Deep Neural Networks (3 of 3)

Impact of Random Weights in Deep M L P

The Effect of Pre-training Network Parameters on Improving Results of a Classification-Type Deep Neural Network.

More hidden layers versus more neurons?

Application Case 6.5 (1 of 2)

Georgia D O T Variable Speed Limit Analytics Help Solve Traffic Congestions

Discussion Questions:

What was the nature of the problems that G D O T was trying to solve with data science?

What type of data do you think was used for the analytics?

What were the data science metrics developed in this pilot project? Can you think of other metrics that can be used in this context?

Application Case 6.5 (2 of 2)

Georgia D O T Variable Speed Limit Analytics Help Solve Traffic Congestions

Convolutional “Deep” Neural Networks

Most popular M L P-base D L method

Used for image/video processing, text recognition

Has at least one convolution weight function

Convolutional layer

Convolutional layer  Polling (sub-sampling)

Consolidating the large tensors into one with a smaller size-and reducing the number of model parameters while keeping only the important features

There can be different types of polling layers

Convolution Function

Typical Convolutional Network Unit

Convolution of a 2 x 2 Kernel by a 3 x 6 Input Matrix

Image Processing Using C N N (1 of 3)

ImageNet (http://www.image-net.org)

Architecture of AlexNet, a C N N for Image Classification

Image Processing Using C N N (2 of 3)

Conceptual Representation of the Inception Feature in GoogLeNet

Image Processing Using C N N (3 of 3)

Examples of Using the Google Lens

Figure 6.28 Two Examples of Using the Google Lens, a Service Based on Convolutional Deep Networks for Image Recognition.

Application Case 6.6

From Image Recognition to Face Recognition

Discussion Questions:

What are the technical challenges in face recognition?

Beyond security and surveillance purposes, where else do you think face recognition can be used?

What are the foreseeable social and cultural problems with developing and using face recognition technology?

Text Processing Using C N N (1 of 2)

Google word2vec project

Word embeddings

Typical Vector Representation of Word Embeddings in a Two-Dimensional Space

Text Processing Using C N N (2 of 2)

C N N Architecture for Relation Extraction Task in Text Mining

Recurrent Neural Networks (R N N) & Long Short-Term Memory (L S T M) (1 of 3)

R N N designed to process sequential inputs

Typical recurrent unit

Recurrent Neural Networks (R N N) & Long Short-Term Memory (L S T M) (2 of 3)

L S T M is a variant of R N N

In a dynamic network, the weights are called the long-term memory while the feedbacks role is the short-term memory

Typical Long Short-Term Memory (L S T M) Network Architecture

Application Case 6.7 (1 of 4)

Deliver Innovation by Understanding Customer Sentiments

Discussion Questions:

Why do you think sentiment analysis is gaining overwhelming popularity?

How does sentiment analysis work? What does it produce?

In addition to the specific examples in this case, can you think of other businesses and industries that can benefit from sentiment analysis? What is common among the companies that can benefit greatly from sentiment analysis?

Recurrent Neural Networks (R N N) & Long Short-Term Memory (L S T M) (3 of 3)

L S T M Network Applications

Example Indicating the Close-to-Human Performance of the Google Neural Machine Translator (G N M T)

Computer Frameworks for Implementation of Deep Learning

Torch (http://www.torch.ch)

M L with G P U

Caffe (caffe.berkeleyvision.org)

Facebook’s improved version (www.caffe2.ai)

TensorFlow (www.tensorflow.org)

Google - Tensor Processing Units (T P U s)

Theano (deeplearning.net/software/ theano)

Deep Learning Group at the University of Montreal

Keras (keras.io)

Application Programming Interface

Cognitive Computing (1 of 3)

Systems that use mathematical models to emulate (or partially simulate) the human cognition process to find solutions to complex problems and situations where the potential answers can be imprecise

I B M Watson on Jeopardy!

How does cognitive computing work?

Adaptive

Interactive

Iterative and stateful

Contextual

Data mining,

Pattern recognition,

Deep learning, and

N L P

Mimic the way the human brain works

Conceptual Framework for Cognitive Computing and Its Promises

Cognitive Computing (2 of 3)

How does cognitive computing differ from A I?

Table 6.3 Cognitive Computing versus Artificial Intelligence (A I).

Characteristic	Cognitive Computing	Artificial Intelligence (A I)
Technologies used	• Machine learning • Natural language processing • Neural networks • Deep learning • Text mining • Sentiment analysis	• Machine learning • Natural language processing • Neural networks • Deep learning
Capabilities offered	Simulate human thought processes to assist humans in finding solutions to complex problems	Find hidden patterns in a variety of data sources to identify problems and provide potential Solutions
Purpose	Augment human capability	Automate complex processes by acting like a human in certain Situations
Industries	Customer service, marketing, healthcare, entertainment, service Sector	Manufacturing, finance, healthcare, banking, securities, retail, government

Cognitive Computing (3 of 3)

Cognitive computing use cases

Development of smart and adaptive search engines

Effective use of natural language processing

Speech recognition

Language translation

Context-based sentiment analysis

Face recognition and facial emotion detection

Risk assessment and mitigation

Fraud detection and mitigation

Behavioral assessment and recommendations, …

Cognitive analytics?

Cognitive Search

Can handle a variety of data types

Can contextualize the search space

Employ advanced A I technologies.

Enable developers to build enterprise-specific search applications

Application Case 6.7 (2 of 4)

I B M Watson Competes against the Best at Jeopardy!

Discussion Questions:

In your opinion, what are the most unique features about Watson?

In what other challenging games would you like to see Watson compete against humans? Why?

What are the similarities and differences between Watson’s and humans’ intelligence?

Application Case 6.7 (3 of 4)

I B M Watson Competes against the Best at Jeopardy!

A High-Level Depiction of Watson’s DeepQ A Architecture

Application Case 6.7 (4 of 4)

I B M Watson Competes against the Best at Jeopardy!

How does Watson do it?

Massive parallelism

Many experts

Pervasive confidence estimation

Integration of shallow and deep knowledge

Future of Watson and Cognitive Computing

Healthcare and medicine

Security and Government

Finance and Retail

Education and Scientific Research, …

End of Chapter 6

Questions / Comments

This work is protected by United States copyright laws and is provided solely for the use of instructors in teaching their courses and assessing student learning. Dissemination or sale of any part of this work (including on the World Wide Web) will destroy the integrity of the work and is not permitted. The work and materials from it should never be made available to students except by instructors using the accompanying text in their classes. All recipients of this work are expected to abide by these restrictions and to honor the intended pedagogical purposes and the needs of other instructors who rely on these materials.

1,111,221,331,

...

nwpwpwpwpb

=+++++

.MsftOfcThm_Text1_Fill { fill:#000000; } .MsftOfcThm_MainDark1_Stroke { stroke:#000000; }