4. Deep Learning : Introduction
• The social dynamics are
characterized by signatures
representing the tweet's popularity,
contagiousness, stickiness, and
interactivity.
• Deep networks have also had
spectacular successes for pedestrian
detection
• Image segmentation yielded
superhuman performance in traffic
sign classification engine
• Detecting Emotions from Photos
• Recommendation engine predicts the
proxy of interest
• Collaborative filtering systems
5. Natural Language
Processing
• Monitor the progress of matters
• Providing lawyers with ready access to the
firm’s prior work product
• Using predictive coding based on a “seed
sample” of documents
• Allowing clients to perform tasks directly
• By extracting content from legal
documents and populating due diligence
summary templates
• Automates the lease abstraction process
• Exporting abstracts to different formats
• Extracts critical information from contracts
• Selection of co counsel based on their
case types
9. Government
• Conditional Cash Transfer
• Bribery
• Payment Programs
• Oversight and Auditing
• Taxpayer
Misrepresentation
• Fraudulent Claims
• Beneficiary Eligibility
• Social Service Programs
• Improper Payments
• Allocation of Public Funds
• Customs Processes
10. Culture, Ethics &
Engagement
• Training Employees
• Citizen Engagement
• Local Engagement
• Citizen Education
• Whistleblowers
• Changing Public
Tolerance
11. Public Procurement
• Purchasing Decisions
• Improper Bidders
• Improving Quality of Goods
• Personal Use of Funds
• Identifying third parties
• Vendor Management
• Beneficial Ownership
13. Crisis Mgmt & Aid
• Recipients
• Fund Distribution
• Tracking Assistance
• Citizen Interests
• Educating Staff
• Prioritizing Resources
• Lack of Critical Infrastructure
14. Cutting the Red Tape
• Redundancies
• Manual Processes
• Consolidating Data
• Commercial Activity
• Feedback
• Land and Property Ownership
• Paper Currency
• Digital Registries
• Manual Processes
15. Transparency
• Disclosed Assets
• Open Contracting
• Unstructured Data
• Cross Country Data
• Data Protection
• Monitoring Transactions
• Intended Use
16. Financial Crime
• Illegal Financial Flows
• Fraud Detection
• Mobile Monitoring
• Counterfeit Money
• Public Official Transparency
17. AI Deep Learning Platform
• Deep Learning Based
• Historical Data is used for prediction and identifying patterns
• Neural Network Algorithms are used
• Image Processing and Natural Language Processing Based Features
• Ensuring Auditability
• Ensuring Security
• Ensuring Privacy
• Ensuring Compliance
• Prevention of identity theft, money laundering and extortion
FERC, CFTC, NERC, HIPAA, SOX
FISMA, FERPA, PCI-DSS, GLBA
PATRIOT ACT, KYC
18. Platform Use Cases
• Measuring creditworthiness of an online identity
• Detecting “typical” behavioral patterns
• Measuring how likely an online identity is real and
trustworthy
• Measuring the depth of the network, based on
interactions with other people and their background.
• Estimating a person's credibility based on her work
history and education.
• Image detection & processing in insurance & fintech
• Natural Language processing for contract analysis
• insurance policy analysis & claim processing
• Advisor for wealth & investment risk management
• investment analysis based on fundamentals &
technicals
19. • Increasing Efficiency
• Better Customer Service
• Cost Reduction
• Profit Making
• Better Productivity
• Compliance monitoring
• Legal and regulatory work automation
• Customer Experience
• Competitive advantage creation
Platform Benefits
26. Deep Learning - Speech
Analysis
• To separate speech from noise, program breaks a
sample into a collection of elements
• Analyzes these units to extract 85 features known to
distinguish speech from other
• Program feeds the features into a deep neural
network trained to classify the units
• Program applies a digital filter that tosses out all the
non-speech units to leave only separated speech
Customer Support
HelpDesk
27. deep neural networks that have
produced spectacular results in
recent years could be
supercharged in coming years by
the addition of memory, attention,
and general knowledge.
SuperCharge Deep Learning
Ruslan Salakhutdinov
28. Training Agents to invent a
Language
Large-scale ML techniques
have led to significant
advances in translation,
verbal reasoning, language
understanding, sentence
generation, and other
areas.
29. “We’ll start to see narrow
artificial intelligence
domains that keep
getting better than the
best human”
Damien Scott,
Stanford University
Singularity
Is singularity truly imminent?
1. Natural Language Generation: Producing text from computer data. Currently used in customer service, report generation, and summarizing business intelligence insights. Sample vendors: Attivio, Automated Insights, Cambridge Semantics, Digital Reasoning, Lucidworks, Narrative Science, SAS, Yseop.
2. Speech Recognition: Transcribe and transform human speech into format useful for computer applications. Currently used in interactive voice response systems and mobile applications. Sample vendors: NICE, Nuance Communications, OpenText, Verint Systems.
3. Virtual Agents: “The current darling of the media,” says Forrester (like Amazon Alexa), from simple chatbots to advanced systems that can network with humans. Currently used in customer service and support and as a smart home manager. Sample vendors: Amazon, Apple, Artificial Solutions, Assist AI, Creative Virtual, Google, IBM, IPsoft, Microsoft, Satisfi.
4. Machine Learning Platforms: Providing algorithms, APIs, development and training toolkits, data, as well as computing power to design, train, and deploy models into applications, processes, and other machines. Currently used in a wide range of enterprise applications, mostly `involving prediction or classification. Sample vendors: Amazon, Fractal Analytics, Google, H2O.ai, Microsoft, SAS, Skytree.
5. AI-optimized Hardware: Graphics processing units (GPU) and appliances specifically designed and architected to efficiently run AI-oriented computational jobs. Currently primarily making a difference in deep learning applications. Sample vendors: Alluviate, Cray, Google, IBM, Intel, Nvidia.
6. Decision Management: Engines that insert rules and logic into AI systems and used for initial setup/training and ongoing maintenance and tuning.
7. Deep Learning Platforms: Currently primarily used in pattern recognition and classification applications supported by very large data sets. Sample vendors: Deep Instinct, Ersatz Labs, Fluid AI, MathWorks, Peltarion, Saffron Technology, Sentient Technologies.
The social dynamics in Twitter are characterized by signatures representing the tweet's popularity, contagiousness, stickiness, and interactivity.
The social dynamics in Yelp are characterized by signatures representing how different groups of reviewers rate individual businesses. We have found the patterns where theses signatures interact by generating, enhancing, or dominating one another.
Deep networks have also had spectacular successes for pedestrian detection and
image segmentation and yielded superhuman performance in traffic sign classification
such as indexation attribution modeling, collaborative filtering, or recommendation
engine
Detect Emotions from Photos
recommendation engine predicts the proxy of interest.
User clicks on ad
user enters a rating
user clicks on a “like” button,
user buys product
user spends some amount of money on the product
user spends time visiting a page for the product
Collaborative filtering systems: when a new item or a new user is introduced, its lack of rating history means that there is no way to evaluate its similarity with other items or users or the degree of association between, say, that new user and existing items. This is called the problem of cold-start recommendations. we get a biased and incomplete view of the preferences of users: we only see the responses of users to the items. they were recommended and not to the other items. In addition, in some cases we may not get any information on users for whom no recommendation has been made (for example, with ad auctions, it may be that the price proposed for an ad was below a minimum price threshold, or does not win the auction, so the ad is not shown at all). More importantly, we get no information about what outcome would have resulted from recommending any of the other items.
FERC, CFTC, NERC, HIPAA or the Health Insurance Portability and Accountability Act, The Sarbanes Oxley Act, Federal Information Security Management Act of 2002 (FISMA), Family Educational Rights and Privacy Act (FERPA), Payment Card Industry Data Security Standard (PCI-DSS), and the Gramm Leach Bliley Act (GLBA)
In last year’s roundup, the focus was almost exclusively on machine intelligence in the virtual world. This time we’re seeing it in the physical world, in the many flavors of autonomous systems: self-driving cars, autopilot drones, robots that can perform dynamic tasks without every action being hard coded. It’s still very early days—most of these systems are just barely useful, though we expect that to change quickly.
These physical systems are emerging because they meld many now-maturing research avenues in machine intelligence. Computer vision, the combination of deep learning and reinforcement learning, natural language interfaces, and question-answering systems are all building blocks to make a physical system autonomous and interactive. Building these autonomous systems today is as much about integrating these methods as inventing new ones.
How do you know what machine learning algorithm to choose for your classification problem? Of course, if you really care about accuracy, your best bet is to test out a couple different ones (making sure to try different parameters within each algorithm as well), and select the best one by cross-validation. But if you’re simply looking for a “good enough” algorithm for your problem, or a place to start, here are some general guidelines I’ve found to work well over the years.
How large is your training set?
If your training set is small, high bias/low variance classifiers (e.g., Naive Bayes) have an advantage over low bias/high variance classifiers (e.g., kNN), since the latter will overfit. But low bias/high variance classifiers start to win out as your training set grows (they have lower asymptotic error), since high bias classifiers aren’t powerful enough to provide accurate models.
You can also think of this as a generative model vs. discriminative model distinction.
Advantages of some particular algorithms
Advantages of Naive Bayes: Super simple, you’re just doing a bunch of counts. If the NB conditional independence assumption actually holds, a Naive Bayes classifier will converge quicker than discriminative models like logistic regression, so you need less training data. And even if the NB assumption doesn’t hold, a NB classifier still often does a great job in practice. A good bet if want something fast and easy that performs pretty well. Its main disadvantage is that it can’t learn interactions between features (e.g., it can’t learn that although you love movies with Brad Pitt and Tom Cruise, you hate movies where they’re together).
Advantages of Logistic Regression: Lots of ways to regularize your model, and you don’t have to worry as much about your features being correlated, like you do in Naive Bayes. You also have a nice probabilistic interpretation, unlike decision trees or SVMs, and you can easily update your model to take in new data (using an online gradient descent method), again unlike decision trees or SVMs. Use it if you want a probabilistic framework (e.g., to easily adjust classification thresholds, to say when you’re unsure, or to get confidence intervals) or if you expect to receive more training data in the future that you want to be able to quickly incorporate into your model.
Advantages of Decision Trees: Easy to interpret and explain (for some people – I’m not sure I fall into this camp). They easily handle feature interactions and they’re non-parametric, so you don’t have to worry about outliers or whether the data is linearly separable (e.g., decision trees easily take care of cases where you have class A at the low end of some feature x, class B in the mid-range of feature x, and A again at the high end). One disadvantage is that they don’t support online learning, so you have to rebuild your tree when new examples come on. Another disadvantage is that they easily overfit, but that’s where ensemble methods like random forests (or boosted trees) come in. Plus, random forests are often the winner for lots of problems in classification (usually slightly ahead of SVMs, I believe), they’re fast and scalable, and you don’t have to worry about tuning a bunch of parameters like you do with SVMs, so they seem to be quite popular these days.
Advantages of SVMs: High accuracy, nice theoretical guarantees regarding overfitting, and with an appropriate kernel they can work well even if you’re data isn’t linearly separable in the base feature space. Especially popular in text classification problems where very high-dimensional spaces are the norm. Memory-intensive, hard to interpret, and kind of annoying to run and tune, though, so I think random forests are starting to steal the crown.
Regardless of whether the learner is a human or machine, the basic learning process is similar. It can be divided into four interrelated components:
Data storage utilizes observation, memory, and recall to provide a factual basis for further reasoning.
Abstraction involves the translation of stored data into broader representations and concepts.
Generalization uses abstracted data to create knowledge and inferences that drive action in new contexts.
Evaluation provides a feedback mechanism to measure the utility of learned knowledge and inform potential improvements.
Machine learning algorithms are divided into categories according to their purpose.
Main categories are
Supervised learning (predictive model, "labeled" data)
classification (Logistic Regression, Decision Tree, KNN, Random Forest, SVM, Naive Bayes, etc)
numeric prediction (Linear Regression, KNN, Gradient Boosting & AdaBoost, etc)
Unsupervised learning (descriptive model, "unlabeled" data)
clustering (K-Means)
pattern discovery
Semi-supervised learning (mixture of "labeled" and "unlabeled" data).
Reinforcement learning. Using this algorithm, the machine is trained to make specific decisions. It works this way: the machine is exposed to an environment where it trains itself continually using trial and error. This machine learns from past experience and tries to capture the best possible knowledge to make accurate business decisions. Example of Reinforcement Learning: Markov Decision Process.
Predictive model
A predictive model is used for tasks that involve the prediction of one value using other values in the dataset. The learning algorithm attempts to discover and model the relationship between the target feature (the feature being predicted) and the other features. Despite the common use of the word "prediction" to imply forecasting, predictive models need not necessarily foresee events in the future. For instance, a predictive model could be used to predict past events, such as the date of a baby's conception using the mother's present-day hormone levels. Predictive models can also be used in real time to control traffic lights during rush hours.
Because predictive models are given clear instruction on what they need to learn and how they are intended to learn it, the process of training a predictive model is known as supervised learning. The supervision does not refer to human involvement, but rather to the fact that the target values provide a way for the learner to know how well it has learned the desired task. Stated more formally, given a set of data, a supervised learning algorithm attempts to optimize a function (the model) to find the combination of feature values that result in the target output.
So, supervised learning consist of a target / outcome variable (or dependent variable) which is to be predicted from a given set of predictors (independent variables). Using these set of variables, we generate a function that map inputs to desired outputs. The training process continues until the model achieves a desired level of accuracy on the training data. Examples of Supervised Learning: Regression, Decision Tree, Random Forest, KNN, Logistic Regression etc.
The often used supervised machine learning task of predicting which category an example belongs to is known as classification. It is easy to think of potential uses for a classifier. For instance, you could predict whether:
An e-mail message is spam
A person has cancer
A football team will win or lose
An applicant will default on a loan
In classification, the target feature to be predicted is a categorical feature known as the class, and is divided into categories called levels. A class can have two or more levels, and the levels may or may not be ordinal. Because classification is so widely used in machine learning, there are many types of classification algorithms, with strengths and weaknesses suited for different types of input data.
Supervised learners can also be used to predict numeric data such as income, laboratory values, test scores, or counts of items. To predict such numeric values, a common form of numeric prediction fits linear regression models to the input data. Although regression models are not the only type of numeric models, they are, by far, the most widely used. Regression methods are widely used for forecasting, as they quantify in exact terms the association between inputs and the target, including both, the magnitude and uncertainty of the relationship.
Descriptive model
A descriptive model is used for tasks that would benefit from the insight gained from summarizing data in new and interesting ways. As opposed to predictive models that predict a target of interest, in a descriptive model, no single feature is more important than any other. In fact, because there is no target to learn, the process of training a descriptive model is called unsupervised learning. Although it can be more difficult to think of applications for descriptive models, what good is a learner that isn't learning anything in particular - they are used quite regularly for data mining.
So, in unsupervised learning algorithm, we do not have any target or outcome variable to predict / estimate. It is used for clustering population in different groups, which is widely used for segmenting customers in different groups for specific intervention. Examples of Unsupervised Learning: Apriori algorithm, K-means.
For example, the descriptive modeling task called pattern discovery is used to identify useful associations within data. Pattern discovery is often used for market basket analysis on retailers' transactional purchase data. Here, the goal is to identify items that are frequently purchased together, such that the learned information can be used to refine marketing tactics. For instance, if a retailer learns that swimming trunks are commonly purchased at the same time as sunglasses, the retailer might reposition the items more closely in the store or run a promotion to "up-sell" customers on associated items.
The descriptive modeling task of dividing a dataset into homogeneous groups is called clustering. This is sometimes used for segmentation analysis that identifies groups of individuals with similar behavior or demographic information, so that advertising campaigns could be tailored for particular audiences. Although the machine is capable of identifying the clusters, human intervention is required to interpret them. For example, given five different clusters of shoppers at a grocery store, the marketing team will need to understand the differences among the groups in order to create a promotion that best suits each group.
Lastly, a class of machine learning algorithms known as meta-learners is not tied to a specific learning task, but is rather focused on learning how to learn more effectively. A meta-learning algorithm uses the result of some learnings to inform additional learning. This can be beneficial for very challenging problems or when a predictive algorithm's performance needs to be as accurate as possible.
The following table lists only a fraction of the entire set of machine learning algorithms.
Model Learning task
Supervised Learning Algorithms
Nearest Neighbor Classification
Naive Bayes Classification
Decision Trees Classification
Classification Rule Learners Classification
Linear Regression Numeric prediction
Model Trees Numeric prediction
Regression Trees
Neural Networks Dual use
Support Vector Machines Dual use
Unsupervised Learning Algorithms
Association Rules Pattern detection
k-means clustering Clustering
Meta-Learning Algorithms
Bagging Dual use
Boosting Dual use
Random Forests Dual use
To begin applying machine learning to a real-world project, you will need to determine which of the four learning tasks your project represents: classification, numeric prediction, pattern detection, or clustering. The task will drive the choice of algorithm. For instance, if you are undertaking pattern detection, you are likely to employ association rules. Similarly, a clustering problem will likely utilize the k-means algorithm, and numeric prediction will utilize regression analysis or regression trees.
Useful links
10 Machine Learning Algorithms Explained to an 'Army Soldier'
Essentials of Machine Learning Algorithms (with Python and R Codes)
What is the difference between labeled and unlabeled data? - Stack Overflow
A Tour of Machine Learning Algorithms
Types of Machine Learning Algorithms