In order to prove that the objective function in Eqn. 1 is non-normal, non-negative, non-monotone, and submodular, we need to prove the following: any one of the terms in the objective is non-normal all the terms in the objective are non-negative any one of the terms in the objective is non-monotone all the terms in the objective are submodular Non-normality Let us consider the term f This metric can never be negative by definition. This is clearly a diminishing returns function i.e., more additional instances in the data are covered Before we prove Theorem 2.2, we will first discuss how several previously proposed methods which Eqn.1 can be reduced to the objectives employed by prior approaches which provide instance level Subsuming other objective functions: The objective optimized by Wachter et al. is Higher values of recourse accuracy are desired; lower values of mean fcost are desired. Explanation vs. Recourse Accuracy for COMP AS (left), Credit (middle), and Bail (right) datasets A.2.2 User Study We manually constructed a two level recourse set (as our black box model) for the bail application. We deliberately ensured that this black box was biased against individuals who are not Caucasian. This two level recourse set (black box) is shown in Figure 4. We used AR-LIME as a comparison point in our user study.

TOKYO, JAPAN - King Felipe VI shakes hands with an ASIMO robot during their visit to the National Museum of Emerging Science and Innovation (Miraikan) in Tokyo, Japan. If you were a bank teller in the '90s, there's a good chance you were terrified. ATMs were sprouting up everywhere, allowing people to withdraw cash without talking to a soul. Bank tellers, it was thought, would go the way of milkmen, lamplighters, and switchboard operators. But automation didn't kill the bank teller.

The jobs at highest risk are those in the transport and retail sectors. In fact the transport sector could have 1.5 million jobs, that's 74% of the current workforce, replaced with automation and 60% of retail. Not surprising when you see how popular online shopping has become - who needs a high street shop? Almost 750,000 have been lost in manufacturing to automation just in the last 15 years alone. Even Stephen Hawking the renowned scientist fears that AI or Artificial Intelligence could eventually spell the end of the human race.

The writer argues that artificial intelligence will steal our jobs – and it may be the best thing that will ever happen to us. We are living on the brink of a fourth industrial revolution argued Klaus Schwab, the Executive Chairman of the World Economic Forum, recently. Like the revolutions of the past – from steam engine to electricity and digitalization, the coming earthquake will fundamentally alter the way we work. The supreme commander of the incoming revolution is artificial intelligence. Two aspects differentiate the coming tsunami from the past ones.