Category Archives: consulting

How to Think Like a Deep Learner – Two Basic Figures – Part1

This discussion is based on some understanding of ANN.  If ANN is not clear, this is not for you, for now.  Also, to be crisp, I will not belabor various nuances of terminology, meaning, and reasoning, at this time; there is a place for that.  This is to let data analysis practitioners understand why and what of deep learning.

Also, the discussion is based on the publication mentioned below.  This is a classic and encourage ML enthusiasts and statisticians to read and learn the mind of a deep learning analyst.

Learning Deep Architectures for AI (Foundations and Trends(r) in Machine Learning) Paperback – October 28, 2009

by Yoshua Bengio

from which I picked up two important pictures to put the key points forward.  These are two different aspects of understanding how to think in Deep Learning.  This is a start, not a complete presentation.   This should lead to some important good questions to further understand the nuances.

I selected the order of the figures to explain my purpose, though the book has it in different order as a mathematical exposition.

Deep learning is deep, because, you want to keep on training on the depths until the learning algorithm achieves a level of certain acceptable predictability.

Learning in polynomial circuit means the following structure.

Take a look at this Figure.

DL_Type1_Nonlinears

The input layer is at the bottom, first level interaction is next layer, additions of all interactions is another layer.  The picture does not easily point out directly other interactions.  For example, x1x4 and also higher levels of interactions, such as x1x2x4.   You may think that such interactions fell off in the feature selection process; and/or it is coming through at a higher level with a different activation relationship.  For example, at the top most level in the picture, we have x1 and x4 coming together in a particular way, but that may be an artificial exhibition of the starting point of the construct.   None the less, the picture, though elegant, is a difficult and incomplete way how a deep learner looks at (all) possibilities. But that is not an issue, as long as we get the point.  The important point is there are countably infinite possibilities!  We will make it finite, by clever intrusion on the intrusion of possibilities.

In essence, considering interactions are represented as a split in a decision tree, you may think of deep search process for a specific collection of all possible roots of a tree, and one beautiful representation of deep thinking is that it is supposed to learn without training; figuring out “labels”. The mathematics above helps in that sense.

The second picture I want to share with you is the following.

DL_Type2_Nonlinears

The above figure explains how to define layers.

The important point here is that every representation, however simple it may look like should be considered as a layer.  In an unsupervised machine learning context, this rule becomes easier to understand, where we want to take out any trace of human judgement.  The result of this is lots of layers to train.

This is especially needed in unsupervised methods, where learning is very difficult and accordingly one has to keep trying different transformations (and all possible transformations with in a construct of a machine)

So the first question is “When do I stop”?

Stop, when the algorithm learned enough.  That is ok, because that is the purpose of the gift of reducing cost of raising computing power.

Does it take billion samples?  So be it.  That attitude is the right thing to appreciate.  We solve a problem; a difficult problem of how to get a machine to learn itself.  Boy, this baby does not need a parent.  It learns itself, though it may take billion exposures, as in the case of computer vision.  That is in no way different from our own evolution.

… Part 2 coming with programming codes and a simple application.

Special Readings for Consulting in Analytics Solution Development and Implementation – DL 498

Required Readings

=============================================================================

I have been writing these articles on CRM over a period of 10 years, and I will move some of the following to the above required list:

=============================================================================

 Predictive Modeling: Myths on Increasing the Predictive Power

 Modeling Process Flow

 CRM Intelligence – Real Time CRM Intelligence and Real Time CRM Best Practices

 Sampling Methods, Inferences, and SAS Procedures for Discrete – Categorical – Response Data

 Interaction term vs. interaction effect in logit and probit models – using STATA to compute the interaction effects – Too technical and you may skip

 Web analytics best practices for marketing and creative – Part 1

 Analysis of Longitudinal Data – Part1.ppt

 A Class of Natural Plots for Marketing Regressions – N-plot.pdf

 Top 10 – Minimal SAS Tutorial Documents – Examples – A Statistician List

PROC SQL Lecture

 Strategies for CRM and Direct Marketing Analytics – Critical Approach and Guidelines

Bayes Theorem, Autoregressive Modeling, and Marketing Optimal Messaging

 Real Time Analytics – Basics of Updating Algorithms

 CRM portals, Analytics, and Direct Marketing Principles are Critical for a Real Time CRM-Direct Marketing Platform

 Pharmaceutical Marketing Mix Models

 Some Principles of Building Pharmaceutical and Non-Pharmaceutical Acquisition Models

 Pharma CRM – Pharmaceutical CRM

 Pharmaceutical CRM – Why Patient Relationship Management is key for product differentiation and competitive advantage?

 CRM Portal, CRM Data Capture, CRM Analytics – Rapid Implementation of Real Time CRM – Part II – Operational CRM

 Pharmaceutical CRM – Differentiate the Product or Die or Do Customer Care.html

 Lead Generation – Consumers – Patients – Optimal Channels for Better ROI – US Mail, Web, Media

 CRM Portal, CRM Data Capture, CRM Analytics-CRM Implementation Requirements

 Marketing Portals – An integrated marketing gateway to a marketing operation

 Optimal Sample Size for Direct Marketing – Some Basics

 Neural Network Approach to Model building – CRM analysis

 Hierarchical Cluster Analysis

 What are the types of CRM analytics?

 Web marketing intelligence – Do you know the effectiveness of your advertisement dollars spent with GOOGLE and OVERTURE sponsorship placements

 Contents of  real time CRM for rapid implementation – Customer Perspective – Part I

 Strategies for CRM and Direct Marketing Analytics – Marketing Options Model

 ROI Trends – Free Tools for Real Time Web Marketing Analytics

 Real Time CRM, Right Time CRM, Customer Relevant Time CRM – Your Priority is…

 Data Hub, Information Hub, Knowledge Hub – Integrated Real Time CRM system.pdf

 Basics of Real Time CRM Intelligence and Real Time CRM Best Practices

 CRM Data Mining – Methods of Dimensionality Reduction and Choosing a Right Technique.

 What is meant by best practices in CRM and/or database marketing.

 Why Real Time CRM is Feasible, Not an Information Overload, and Worth It?.

 Is it CRM software or CRM vendor or CRM implementation?.

 Evaluating your email (e-mail) marketing best practices and fast track adjustments.

 Test for evaluating the state of best practices for your CRM implementation and solution for fast track alignment.

 Web Marketing is Key for Direct Marketing.

 Real Time Analysis, Content delivery, and Data Capture Powers CRM portals.

 Building Real Time CRM intelligence: Some Key Analytics and Strategies.

 TEN REASONS WHY MODELS MAY FAIL.

 Architecture for e-Commerce strategy – Questions and Answers Demystifying Structurally Strong E-Commerce Architecture..

 Using Customer Care to Differentiate a Pharmaceutical Product From Its Competition.

 Why Companies Need Analytics? – Facets of Getting to Useful Analytics.

 Foundations of Database Best Practices for Analytics in CRM Setup.

Where does quality meet CRM?