Mabble Rabble: 2018

25 December 2018

MemeTrackers

Memetracker
Techmeme
Memeorandum
knowyourmeme
memeburn
memebuster
nifty

22 December 2018

20 December 2018

15 December 2018

14 December 2018

Document Similarity Measures

String Matching

Edit Distance

Levenstein
Smith-Waterman
Affine

Alignment

Jaro-Winkler
Soft-TFIDF
Monge-Elkan

Phonetic

Soundex
Translation

Distance Matching

Euclidean
Manhattan
Minkowski

Text Analytics

Jaccard
TFIDF
Cosine Similarity

Relational Matching

Set Based

Dice
Tanimoto (Jaccard)
Common Neighbors
Adar Weighted

Aggregates

Average values
Max/Min values
Medians
Frequency (Mode)

Other Matching

Numeric distance
Boolean equality
Fuzzy matching
Domain specific

Gazettes

Lexical matching
Named Entities (NER)

13 December 2018

Internet of Blockchains

why the net giants are worried about the web 3.0

Beyond Word Embeddings

Bert
Skip-Thoughts
Quick-Thoughts
USE
Infersent
ELMO

Universal Word Sentence Embeddings
Sentence Embedding Evaluations
Sentence Embedding Baselines
Illustrated Bert
Deep Meaning Beyond Thought Vectors
Word Vectors NLP Modeling From BOW to Bert
An overview of neural nlp milestones

12 December 2018

7 October 2018

Types of Deep Learning

Type	Group
Attentional Interface	Attention-Memory
Memory-Attention Networks	Attention-Memory
One-Shot Associative Memory	Attention-Memory
KeyValue Memory Networks	Attention-Memory
Compositional Attention Network	Attention-Memory
Deep Memory Network	Attention-Memory
Structured Attention Network	Attention-Memory
Hyperbolic Attention Network	Attention-Memory
Multi-Cast Attention Network	Attention-Memory
Bi-Directional Attention Flow	Attention-Memory
Variational Autoencoder	Autoencoder
Autoencoder	Autoencoder
Denoising Autoencoder	Autoencoder
Sparse Autoencoder	Autoencoder
Contrastive Autoencoder	Autoencoder
Feedforward	Basic
Perceptron	Basic
Multilayer Perceptron	Basic
Deep Convolutional Network	CNN
Convolutional Deep Belief Network	CNN
Convolutional GAN	CNN
DeConvolutional Network	CNN
Deep Convolutional Inverse Graphics Network	CNN
Geometric Deep Learning	CNN
Convolutional Kernel Networks	CNN
Convolutional Autoencoder	CNN
Hierarchical Convolutional Deep Maxout Network	CNN
Deep Belief Network	DBN
Continuous DQN	DQN
Deep Q Network	DQN
Dueling DQN	DQN
Episodic-Memory DQN	DQN
Bidirectional LSTM	LSTM
Convolutional LSTM	LSTM
Grid LSTM	LSTM
Long Short Term Memory	LSTM
Peephole LSTM	LSTM
Phrasal LSTM	LSTM
Hierarchical LSTM	LSTM
Gated Recurrent Unit	LSTM
Adaptive Resonance Theory	Modular
Maximum Entropy	Modular
Counterpropogation	Modular
Spline	Modular
Gaussian	Modular
Neocognitron	Neural
Neural Programmer	Neural
Neural Turing Machine	Neural
Neuro-Fuzzy	Neural
Neuroevolution	Neural
Neural Associative Memory	Neural
Neural Hawkes Process Memory	Neural
Sequence-2-Sequence	Other
Deep Feedforward	Other
Deep Neural Network	Other
Helmholtz Machine	Other
Hopfield Network	Other
Kohonen Network	Other
Compound Hierarchical Deep Model	Other
Dense Associative Memory	Other
Hierarchical Temporal Memory	Other
Large Memory Storage and Retrieval Network	Other
Generative Adversarial Network	Other
Associative Neural Network	Other
Adaptive Computation Time	Other
Deep Coding Network	Other
Deep Deterministic Policy Gradient	Other
Deep Predictive Coding Network	Other
Deep Reservoir Computing	Other
Deep Residual Network	Other
Deep Stacking Network	Other
Diffusion Network	Other
Echo state Network	Other
Elman Jordan Network	Other
Extreme Learning Machine	Other
Instantaneously Trained Neural Network	Other
Learning Vector Quantization	Other
Liquid State Machines	Other
Spiking Neural Network	Other
Tensor Deep Stacking Network	Other
Radial Basis Function	Other
Recursive Neural Network	Other
Markov Chain	Probabilistic
Deep Bayesian Neural Network	Probabilistic
Deep Markov Model	Probabilistic
Stochastic Neural Network	Probabilistic
Spike and Slab RBM	RBM
Boltzmann Machine	RBM
Restricted Bolzmann Machine	RBM
Bidirectional RNN	RNN
Clockwork RNN	RNN
Continuous Time RNN	RNN
Dilated RNN	RNN
Hierarchical RNN	RNN
Recurrent Neural Network	RNN
Second Order RNN	RNN
Multi-Time Scales RNN	RNN
Recurrent Multilayer Perceptron	RNN
Deep Kernel Machine	SVM
Support Vector Machine	SVM
Shallow Neural Networks	ThoughtVectors/WordVectors

*Shallow = one hidden layer in NN

*Deep = more than one hidden layer in NN

8 September 2018

27 August 2018

100 Most Influential Works in Cognitive Science

9 August 2018

Geometric Deep Learning

Geometric Deep Learning
Geometric Deep Learning: Going Beyond Euclidean Data
Geometric Deep Learning Slideshare
SplineCNN: Fast Geometric Deep Learning
Poincaré Embeddings

16 July 2018

Lorempixel

Lorempixel

Free random image generators...

15 July 2018

Game Theory Optimal

Approximating Game-Theoretic Optimal Strategies
Cepheus and Computer Poker Algorithms
GTO vs Exploitative Play
Safe and Nested Subgame Solving
Depth-Limited Solving

7 July 2018

Mailer Campaign Uplift Modeling

Profit(C) = ExpectedProfit(C) x [P(B | V) - P(B | C)] - AdCost(C)

P(B | C) - probability of buying given control without ad campaign (Naive Bayes)
ExpectedProfit(C) - profit to make from customer if they decide to buy (Regression)
P(B | V) - probability of buying given variant of ad campaign (Naive Bayes)
AdCost(C) - cost to mail campaign to customer as a constant
likely to take into account market or customer segmentation
regression could be either logistic or linear
total profit would be determined by how much the customer decided to buy either with control and/or ad campaign
optimization of ad campaign given the customer conversion ratio
use customer data as part of expected profit measures for average spend
additionally, more ways to approach the same contextual measures of profit

uplift modelling

3 July 2018

Test-Driven Machine Learning

TDD -> Kent Beck
BDD -> Dan North
Refactoring -> Martin Fowler
Agile -> James Shore

Random processes in machine learning need to be measured and controlled, various simple testing strategies can make this possible.

24 June 2018

Probabilistic Reasoning

Factorie (Scala)
Figaro (Scala)
PyMC4 (Python)
PyMC3 (Python)
Probability (Python)
BayesLoop (Python)
Tweety (Java)
Dimple (Java)
Chimple (Java)
WebPPL (JavaScript)

Probabilistic Programming and Bayesian Methods for Hackers
The Design and Implementation of Probabilistic Programming Languages

Natural Computation

Cellular Automata
Evolutionary Computation
Swarm Intelligence
Artificial Immune Systems
Artificial Life
Quantum Computing
Systems Biology
Synthetic Biology
Cellular Computing
DNA Computing
Amorphous Computing
Membrane Computing
Neural Computation

Global Optimization

Essentials of Metaheuristics

18 June 2018

Mining Knowledge Graphs from Text

Entity Linking and Disambiguation

Natural Language Understanding

16 June 2018

Generative Models

Hidden Markov Model
Gaussian Mixture Model
Naive Bayes
Latent Dirichlet Allocation
Restricted Boltzmann Machines
Generative Adversarial Networks
Variational Autoencoder
Probabilistic Context Free Grammar
Generative Long-Short-Term-Memory
Helmholtz Machine

13 June 2018

4 June 2018

Markov Chain Monte Carlo Sampling

Metropolis-Hastings
Gibbs Sampling
Slice Sampling
Reversible-Jump
Multiple-Try Metropolis
Langevin Rule
Hamiltonian
Simulated Tempering

One can utilize the various macro-environmental factors to evaluate demand forecasting. The below list the various types. However, they are invariably grouped under PEST, PESTEL, PESTLE, SLEPT, STEPE, STEEPLE, STEEPLED, DESTEP, SPELIT, STEER. B2B market places tend to be affected more by social factors. Defense contractors tend to be affected by political factors. Factors that are more frequent or volatile may have higher importance. Conglomerates may tend to divide factors by departmental assessment or even specific to a geographical location. One can use these models to connect with micro-environmental and internal factors. Additionally, SWOT analysis may also be used: Strength, Weakness, Opportunities, Threats.

Political
Social
Economic
Technological
Legal
Environmental
Demographics
Regulatory
Inter-cultural
Ethical
Educational
Physical
Religious
Security
Competition
Ecological
Geographical
Historical
Organizational
Temporal

22 May 2018

Bandit Algorithms

15 May 2018

TheStreet

11 May 2018

Top Performing MultiAsset Funds

Top performing multiasset funds

Google Cloud Client Libraries for Python

6 May 2018

Common Deep Learning Recipe

Specification of Dataset
Cost Function
Optimization Procedure
Model

4 May 2018

Gluon

Sonnet

3 May 2018

Geographical Information Tools

ARCGIS
GEOServer
QGIS
GEOSPARQL
SWEET Ontologies
GML
List of GIS Data Sources
GeoNames
PostGIS
OpenLayers
Google Maps
Leafletjs
MapBox
GeoJSON
Shapefile
OGR

1 May 2018

Vulnerabilities in Deep Learning

Security Risks in Deep Learning Implementations

Deep Learning Based Vulnerability Detection
6 ways hackers will use machine learning to launch attacks
Vulnerability of Deep Learning
Further Deep Learning Security Papers

30 April 2018

Structured Prediction

Graphical Models

Bayesian Networks
Markov Networks

Inference Methods

Message Passing
Integer Programs
Dynamic Programming
Variational Methods

Classical Discriminative Learning

Structured SVM
Structured Perceptron
Conditional Random Fields

Non-Linear Approaches

Structured Random Forests
Deep Structured Prediction

More Complex Structures

Hierarchical Classification
Sequence Prediction/Generation

Application Areas

Computer Vision
Speech Recognition
Natural Language Processing
Bioinformatics

27 April 2018

Factset

Money.net

Investsnips

NBTrader

Trading View

DigitalLook

Digital Look

MoneyAM

Funds Library

25 April 2018

Common Machine Learning Algorithms

Linear Regression
Logistic Regression
Decision Tree
SVM
Naive Bayes
kNN
K-Means
Random Forest
Dimensionality Reduction Algorithm
Gradient Boosting Algorithms

GBM
XGBoost
LightGBM
CatBoost

Terrorism Data

Global Terrorism Database
Global Database of Terrorism Incidents
GTD Dataset
Terrorism Cases 2001-2016
Terrorism Organization Profiles
Data World Datasets on Terrorism
Terrorist and Insurgent Organization Social Services (TIOS)
An Inventory of Databases and Datasets on Terrorism Events
Predicting Terrorism
Terrorism Datasets
Global Terrorism Index 2017
IARPA - DIVA
Countering Lone Actor Terrorism

24 April 2018

AlphaGo Zero

Reinforcement Learning Cheatsheet

Predictive Algorithms

AI Cheatsheets

Neural Network Cells

Tensorflow Cheatsheet

Machine Learning Cheatsheet

Big-O Notation

ScikitLearn

Neural Network Graphs

Standard Data Science Algorithms

20 April 2018

Consumer Protection

A few areas of consumer protection that provide for certain indicators of measure for rights of consumers, fair trading practices, competition, and accurate information in the marketplace:

Access
Complaints Handling
Dispute Resolution and Redress
Economic Interests
Education and Awareness
Empowerment Index
Protection Index
Fraud Detection
Governance and Participation
Information and Transparency
Verifiable Practices and Standards
Privacy and Data Security
Safety and Reliability
Product and Service Reviews

Identity and Access Management

Tools:

OpenAM
OpenSSO
Shibboleth
OpenDJ
OpenIDM

A Few Machine Learning Use Cases in IAM:

Provisioning accounts and permissions management
Dynamic risk scoring
Identification of Friend or Foe
Fraud and Threat patterns via detection of anomalies
Feature Engineering (attributes, subjects, resources, environments, roles, entitlements)
Rule profiling using decision functions
Clustering to identify threshold patterns, excess, shared identity attributes, overlaps
Potential for use with blockchain for digital identity and trust
Deep identification with biometrics and fingerprints
Mining for visibility of IAM and Security Information and Event Management

18 April 2018

Consumer Behavior

Consumer spending behavior is directly correlated to household income that dictates disposable income. One can build a user profile of consumers with a set of attributes that could be contextualized towards specific market trends. Globally different regions have their own taxation. But, invariably to map an entire user behavior one would have to look at an entire calendar period - day, week, month, year. So, in UK this would pertain to the April-to-April tax year. By doing this one can obtain clearer set of patterns during bank holidays, weekends, weekdays, seasonal, social events, and other periods to glean on specific contextual behaviors. Once an anonymized user is mapped to Y1 the following Y2, Y3, Yn could be mapped to discover historical trends. Using machine learning approaches like clustering can provide for a means of visualization of complex networks to identify churn, segmentation, and intents for conversion. Additionally, semantic enrichment could provide further context for answering specific data science questions and end-to-end predictive storytelling. From looking at big data standpoint it would certainly help to process batch and in stream mode. However, one would have to take into account the difference between processing and event time of recorded behavior as well as to maximize in-memory computation. The below highlight key indicators that could be analyzed for consumer behavior.