Category Archives: AI

Machine Learning Models – Bias Mitigation Strategies

Machine learning models - Bias mitigation strategies

In this post, you will learn about some of the bias mitigation strategies which could be applied in ML Model Development lifecycle (MDLC) to achieve discrimination-aware machine learning models. The primary objective is to achieve a higher accuracy model while ensuring that the models are lesser discriminant in relation to sensitive/protected attributes. In simple words, the output of the classifier should not correlate with protected or sensitive attributes. Building such ML models becomes the multi-objective optimization problem. The quality of the classifier is measured by its accuracy and the discrimination it makes on the basis of sensitive attributes; the more accurate, the better, and the less discriminant (based on sensitive attributes), the better. The following are some of …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

Facebook Machine Learning Tool to Check Terrorists Posts

Facebook ML System Integrity Compromised

In this post, you will learn about details on Facebook machine learning tool to contain online terrorists propaganda. The following topics are discussed in this post: High-level design of Facebook machine learning solution for blocking inappropriate posts Threat model (attack vector) on Facebook ML-powered solution ML Solution Design for Blocking Inappropriate Posts The following is the workflow Facebook uses for handling inappropriate messages posted by terrorist organizations/users. Train/Test a text classification ML/DL model to flag the posts as inappropriate if the posts is found to contain words representing terrorist propaganda. In production, block the messages which the model could predict as inappropriate with very high confidence. Flag the messages for data analysts processing if the …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

ML Model Fairness Research from IBM, Google & Others

In this post, you would learn about details (brief information and related URLs) on some of the research work done on AI / machine learning model ethics & fairness / bias in companies such as Google, IBM, Microsoft and others. This post will be updated from time-to-time covering latest projects/research work happening in various companies. You may want to bookmark the page for checking out latest details. Before we go ahead, it may be worth visualizing the great deal of research happening in the field of machine learning model fairness represented using the cartoon below, which is taken from the course CS 294: Fairness in Machine Learning course taught at UC Berkley. IBM Research for ML Model Fairness AI Fairness 360 - AIF360: AIF360 Toolkit is aimed to help data scientists, not only detect biases at different points (training data, classifier and predictions) in machine learning pipeline but also apply bias mitigation strategies to handle any discovered bias. Here is the link for AIF360 Portal Trusted AI Research: List down research publications and related work in the following areas: Robustness (Security & reliability of AI systems) Fairness Explainability / Interpretability Trackability (Lineage) AI Fairness Tutorials: Presents tutorials with the following projects: Credit scoring Medical expenditure Gender classification of face images AI Model Fairness research papers based on which AIF360 toolkit is created. Google Research/Courses on ML Model Fairness Here are some links in relation to machine learning model fairness. Machine learning fairness Google Machine Learning crash course - Fairness module: In addition, the module also presents information on some of the following: Types of Bias. Discussed are some of the following different types of bias: Selection bias (coverage bias, non-response bias, sampling bias) Group attribution bias (in-group bias, out-group homogeneity bias) Implicit bias (confirmation & experimenter's bias) Identifying bias: The following are some of the topics discussed for identifying the bias: Missing feature values Unexpected feature values Data skew Evaluating Bias: Confusion matrix (accuracy vs recall or sensitivity) could be used to evaluate bias for different groups. Interactive visualization on attacking discrimination with smarter machine learning Microsoft Research on Model FATE FATE: Defines initiatives in relation to some of the following: Fairness Accountability Transparency Ethics Kate Crawford - The Rise of Autonomous Experimentation: Technical, Social, and Ethical Implications of AI. Details & some great videos could be found on Kate Crawford Website. Hanna Wallach - Work on FATE Summary In this post, you learned about details on courses and research initiatives happening in the area of machine learning model fairness in different companies such as Google, IBM and others.

In this post, you would learn about details (brief information and related URLs) on some of the research work done on AI/machine learning model ethics & fairness (bias) in companies such as Google, IBM, Microsoft, and others. This post will be updated from time-to-time covering latest projects/research work happening in various companies. You may want to bookmark the page for checking out the latest details. Before we go ahead, it may be worth visualizing a great deal of research happening in the field of machine learning model fairness represented using the cartoon below, which is taken from the course CS 294: Fairness in Machine Learning course taught at UC Berkley. IBM Research for ML Model Fairness …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

Fairness Metrics – ML Model Sensitivity for Bias Detection

Model sensitivity for bias detection

There are many different ways in which machine learning (ML) models’ fairness could be determined. Some of them are statistical parity, the relative significance of features, model sensitivity etc. In this post, you would learn about how model sensitivity could be used to determine model fairness or bias of model towards the privileged or unprivileged group. The following are some of the topics covered in this post: How could Model Sensitivity be used to determine Model Bias or Fairness? Example – Model Sensitivity & Bias Detection How could Model Sensitivity determine Model Bias or Fairness? Model sensitivity could be used as a fairness metrics to measure the model bias towards the privileged or unprivileged group. Higher the …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

Job Description – Chief Artificial Intelligence (AI) Officer

Job description of a Chief AI Officer

Whether your organization needs a chief artificial intelligence (AI) officer is a topic where there have been differences of opinions. However, the primary idea is to have someone who heads or leads the AI initiatives across the organization. The designation could be chief AI officer, Vice-president (VP) – AI research, Chief Analytics Officer, Chief Data Officer, AI COE Head or maybe, Chief Data Scientist etc. One must understand that building AI/machine learning models and deploying them in production is just one part of the whole story. Aspects related to AI governance (ethical AI), automation of AI/ML pipeline, infrastructure management vis-a-vis usage of cloud services, unique project implementation methodologies etc., become of prime importance once you are done with the hiring of data scientists for …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

Bias Detection in Machine Learning Models using FairML

FairML for Bias Detection in Machine Learning Models

Detecting bias in machine learning model has become of great importance in recent times. Bias in the machine learning model is about the model making predictions which tend to place certain privileged groups at a systematic advantage and certain unprivileged groups at a systematic disadvantage. And, the primary reason for unwanted bias is the presence of biases in the training data, due to either prejudice in labels or under-sampling/over-sampling of data. Especially, in banking & finance and insurance industry, customers/partners and regulators are asking the tough questions to businesses regarding the initiatives taken by them to avoid and detect bias. Take an example of the system using a machine learning model to …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

AI / Machine Learning Bias Explained with Examples

machine learning models bias variance vs complexity

In the artificial intelligence (AI) / machine learning (ML) powered world where predictive models have started getting used more often in decision-making areas, the primary concerns of policy makers, auditors and end users have been to make sure that these models are not taking biased/unfair decisions based on model predictions (intentional or unintentional discrimination). Imagine industries such as banking, insurance, and employment where models are used as solutions to decision-making problems such as shortlisting candidates for interviews, approving loans/credits, deciding insurance premiums etc. How harmful it could be to the end users as these decisions may impact their livelihood based on biased predictions made by the model, thereby, resulting in unfair/biased decisions. …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

Security Attacks Analysis of Machine Learning Models

Threat Model - Security Attacks on Machine Learning Models

Have you wondered around what would it be like to have your machine learning (ML) models come under security attack? In other words, your machine learning models get hacked. Have you thought through how to check/monitor security attacks on your AI models? As a data scientist/machine learning researcher, it would be good to know some of the scenarios related to security/hacking attacks on ML models. In this post, you would learn about some of the following aspects related to security attacks (hacking) on machine learning models. Examples of Security Attacks on ML Models Hacking machine learning (ML) models means…? Different types of Security Attacks Monitoring security attacks Examples of Security Attacks on ML Models Most of …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , , .

JupyterLab & Jupyter Notebook Cheat Sheet Commands

jupyter notebook cheat sheet commands

Are you starting to create machine learning models (using python programming) using JupyterLab or Jupyter Notebook? This post list down some commands which are found to be very useful while one (beginner data scientist) is getting started with using JupyterLab notebook for building machine learning models. Notebook Operations: The following command helps to perform operations with the notebook. Ctrl + S: Save the notebook Ctrl + Q: Close the notebook Enter: While on any cell, you want to enter edit mode, press Enter. Cells Operation: The following commands help with performing operations on cells: J: Select the cell below the current cell; This command would be used to go through cells below the …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

Missing Data Imputation Techniques in Machine Learning

Missing Data Imputation Techniques

Have you come across the problem of handling missing data/values for respective features in machine learning (ML) models during prediction time? This is different from handling missing data for features during training/testing phase of ML models. Data scientists are expected to come up with an appropriate strategy to handle missing data during, both, model training/testing phase and also model prediction time (runtime). In this post, you will learn about some of the following imputation techniques which could be used to replace missing data with appropriate values during model prediction time. Validate input data before feeding into ML model; Discard data instances with missing values Predicted value imputation Distribution-based imputation Unique value imputation Reduced feature models Below is the diagram …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

Code of Ethics in Artificial Intelligence (AI) – Key Traits

Code of Ethics for Artificial Intelligence

Do you know that organizations have started paying attention to whether AI/machine learning (ML) models are doing unbiased, safe and trustable predictions based on ethical principles? Have you thought through consequences if AI/machine learning (ML) models you created for your clients make predictions which are biased towards a class of customer, thus, hurting other customers? Have you imagined scenarios in which customers blame your organization of benefitting a section of customers (preferably their competitors), thus, filing a case against your organization and bring bad names and loss to your business? Have you imagined the scenarios when ML models start making incorrect predictions which could result in loss of business? If above …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , , .

AI – Three Different types of Machine Learning Algorithms

Types of machine learning (AI)

This post is aimed to help you learn different types of machine learning algorithms which forms the key to artificial intelligence (AI). Machine learning algorithms Representation or Feature learning algorithms Deep learning algorithms The following represents different types of learning algorithms in form of a Venn diagram. What are Machine Learning (ML) Algorithms? Machine learning algorithms are the most simplistic class of algorithms when talking about AI. ML algorithms are based on the idea that external entities such as business analysts and data scientists need to work together to identify the features set for building the model. The ML algorithms are, then, trained to come up with coefficients for each of the features and how are they …

Continue reading

Posted in AI, Data Science, Machine Learning. Tagged with , .

AI & RPA to Automate the Talent Acquisition Processes

Robots for Talent Acquisition

Artificial Intelligence (AI) is not only finding its usage in almost all the existing business processes but also, enabling business stakeholders and entrepreneurs to think of innovative ideas to come up with new business processes and gain competitive advantage. Robotic Process Automation (RPA) makes use of AI to make intelligent decisions and automate end-to-end business processes to achieve human-like efficiency and effectiveness, thereby, augmenting humans to be more productive and achieve more in less time. Talent acquisition is a business domain where there are many business processes which are repetitive in nature and could make use of AI for business process automation and achieve the goal of greater efficiency and scale. …

Continue reading

Posted in AI, RPA. Tagged with , .

Google Cloud Text-to-Speech Java Code Example

Enable Google Cloud Text-to-Speech Service

Google Cloud Text-to-Speech is a text-to-speech conversion service which got launched a few days back by Google Cloud. This was one of the most important service missing from Google Cloud AI portfolio which is now available and completes the loop for text-to-speech and speech-to-text services by Google Cloud. In next few weeks, you will learn about different usages of Google Cloud text-to-speech service with other Google cloud services. In this post, you will learn about some of the following: Setup Eclipse IDE-based Development Environment Create a Maven or Spring Boot (Spring Starter) Project Setup Eclipse IDE-based Development Environment The following are some of the key aspects of setting up the …

Continue reading

Posted in AI, Cloud, Google Cloud, Java. Tagged with , , .

Build IVR System using Amazon Polly, Lambda and Twilio

Build IVR with Amazon Polly, S3, Lambda and Twilio

Building an intelligent IVR system with a Bot handling the interaction with your end users and bringing in humans based on pre-defined events would bring a lot of automation and remove mundane manual activities which takes up lot of time for a person. This can be achieved using cloud services provided by cloud providers such as Amazon, Google, Azure etc and communication service providers such as Twilio. In this post, you will learn about how to create or build an intelligent or smart IVR system using some of the following: Use Amazon Polly to create one or more custom text-to-speech audios and store the same at predefined locations in AWS …

Continue reading

Posted in AI, AWS, Java, Tutorials. Tagged with , , .

Amazon Polly Text-to-speech with AWS S3, Twilio Java App

Amazon Polly - S3 - Twilio - Spring Boot - Java

Amazon Polly can be used with Twilio phone service and AWS S3 to create an automated alert system which does (achieves) some of the following: Convert text to speech (using Amazon Polly) Upload audio (speech stream) created using Polly service on AWS S3 bucket Use Twilio Call service to play the audio to the destined phone number The following represents the application architecture diagram (communication flow viewpoint) representing communication between  Spring Boot app and Amazon Polly, Amazon S3 and Twilio Service to achieve automated phone alerts based on text-to-speech conversion. This can be used to create automated alert/notification system around following use cases which makes phone call to concerned personal …

Continue reading

Posted in AI, AWS, Java.