Most approaches in algorithmic fairness constrain machine learning methods so the resulting predictions satisfy one of several intuitive notions of fairness. While this may help private companies comply with non-discrimination laws or avoid negative publicity, we believe it is often too little, too late. By the time the training data is collected, individuals in disadvantaged groups have already suffered from discrimination and lost opportunities due to factors out of their control. In the present work we focus instead on interventions such as a new public policy, and in particular, how to maximize their positive effects while improving the fairness of the overall system. We use causal methods to model the effects of interventions, allowing for potential interference--each individual's outcome may depend on who else receives the intervention. We demonstrate this with an example of allocating a budget of teaching resources using a dataset of schools in New York City.

We summarize our recent findings Ghauch et al. (2017), where we proposed a framework for learning a Kolmogorov model, for a collection of binary random variables. More specifically, we derive conditions that link outcomes of specific random variables, and extract valuable relations from the data. We also propose an algorithm for computing the model and show its first-order optimality, despite the combinatorial nature of the learning problem. We apply the proposed algorithm to recommendation systems, although it is applicable to other scenarios. We believe that the work is a significant step toward interpretable machine learning.

Spectral Inference Networks generalize Slow Feature Analysis to generic symmetric operators, and are closely related to Variational Monte Carlo methods from computational physics. As such, they can be a powerful tool for unsupervised representation learning from video or pairs of data. We derive a training algorithm for Spectral Inference Networks that addresses the bias in the gradients due to finite batch size and allows for online learning of multiple eigenfunctions. We show results of training Spectral Inference Networks on problems in quantum mechanics and feature learning for videos on synthetic datasets as well as the Arcade Learning Environment. Our results demonstrate that Spectral Inference Networks accurately recover eigenfunctions of linear operators, can discover interpretable representations from video and find meaningful subgoals in reinforcement learning environments.

Despite their increasing popularity and success in a variety of supervised learning problems, deep neural networks are extremely hard to interpret and debug: Given an already trained deep neural network, and a set of test inputs, how can we gain insight into how those inputs interact with different layers of the neural network? Furthermore, can we characterize a given deep neural network based on its observed behavior on different inputs? In this paper, we propose a novel factorization-based approach on understanding how different deep neural networks operate. In our preliminary results, we identify fascinating patterns that link the factorization rank (typically used as a measure of interestingness in unsupervised data analysis) with how well or poorly the deep network has been trained. Finally, our proposed approach can help provide visual insights on how high-level, interpretable patterns of the network's input behave inside the hidden layers of the deep network.

Get your team access to Udemy's top 2,500 courses anytime, anywhere. "The implementation part is very good and up-too the mark. The explanation step by step process is very good." (February 2018). "course done very well; everything is explained in detail; really satisfied!!!" (February 2018).

Writing programs that can create programs have been an elusive goal of artificial intelligence(AI) research for many years. As a matter of fact, the idea that AI agents can create their own programs if often seem as one of the differentiators of general AI vs. narrow AI. So important is this goal, that AI researchers have created a specific area of research known as Program Synthesis that focuses on addressing those challenges. The idea behind program synthesis is to create AI agents that can generate programs that match a given specification. We often use primitive versions of this technique when we take advantage of, for instance, the Flash Fill feature in Microsoft Excel.

As J.J. Kardwell, founder and CEO of predictive marketing software company EverString, puts it: "Growth-focused sales organizations of every size and stage cannot afford to ignore the benefits of AI-assisted sales." According to research done by Accenture, artificial intelligence is projected to improve labor productivity by as much as 40 percent. It is no surprise that investment in artificial intelligence has increased to $14.9 billion, as of 2014, according to a study conducted by the Bank of America Merrill Lynch. This is projected to increase further by at least 50 percent per year. The same study claims that the innate limitations of humans will make AI the core technology of the so-called "internet of things."

This Neural Network tutorial will help you understand what is a neural network, how a neural network works, what can the neural network do, types of neural network and a usecase implementation on how to classify between photos of dogs and cats. Deep Learning uses advanced computing power and special types of neural networks and applies them to large amounts of data to learn, understand, and identify complicated patterns. Automatic language translation and medical diagnoses are examples of deep learning. Most deep learning methods involve artificial neural networks, modeling how our brains work. Neural networks are built on Machine Learning algorithms to create an advanced computation model that works much like the human brain.

By signing up you agree to receive email newsletters and notifications from MIT Technology Review.