When fed a sufficient amount of training data, artificial intelligence techniques can be used to generate new ideas in several different ways. Is that creativity?

Overfitting in machine learning is a common problem that occurs when a model is trained so much on the training dataset that it learns specific details about the training data that don't generalise well, and cause poor performance on new, unseen data. Overfitting can happen for a variety of reasons, but ultimately it leads to a model that is not able to generalize well and make accurate predictions on data it has not seen before. In this blog post, we will explore the causes of overfitting, the ways in which it can be prevented, and some strategies for dealing with overfitting if it occurs. We will talk about two of the main reasons for overfitting in this article: the model is overly complex, and training is run for too long. In fact, the combination of both of these situations is when overfitting is most prevalent!

We are faced with data comprised of entities interacting over time: this can be individuals meeting, customers buying products, machines exchanging packets on the IP network, among others. Capturing the dynamics as well as the structure of these interactions is of crucial importance for analysis. These interactions can almost always be labeled with content: group belonging, reviews of products, abstracts, etc. We model these stream of interactions as stream graphs, a recent framework to model interactions over time. Formal Concept Analysis provides a framework for analyzing concepts evolving within a context. Considering graphs as the context, it has recently been applied to perform closed pattern mining on social graphs. In this paper, we are interested in pattern mining in sequences of interactions. After recalling and extending notions from formal concept analysis on graphs to stream graphs, we introduce algorithms to enumerate closed patterns on a labeled stream graph, and introduce a way to select relevant closed patterns. We run experiments on two real-world datasets of interactions among students and citations between authors, and show both the feasibility and the relevance of our method.

Pricing decisions are increasingly made by AI. Thanks to their ability to train with live market data while making decisions on the fly, deep reinforcement learning algorithms are especially effective in taking such pricing decisions. In e-commerce scenarios, multiple reinforcement learning agents can set prices based on their competitor's prices. Therefore, research states that agents might end up in a state of collusion in the long run. To further analyze this issue, we build a scenario that is based on a modified version of a prisoner's dilemma where three agents play the game of rock paper scissors. Our results indicate that the action selection can be dissected into specific stages, establishing the possibility to develop collusion prevention systems that are able to recognize situations which might lead to a collusion between competitors. We furthermore provide evidence for a situation where agents are capable of performing a tacit cooperation strategy without being explicitly trained to do so.

Despite their incorporeal form, memories have a way of becoming a very real part of our identity, like the pattern of freckles on your face or your favorite jacket might. Remembering a childhood friend while gazing off at a field of dandelions may be pleasant, but being sucked back into a bad memory -- a difficult breakup or a traumatizing loss -- can be unbearable. But what if, a la Eternal Sunshine of the Spotless Mind, we could simply erase those memories? It's something being explored, but Philipp Kellmeyer, a neurologist and head of the Neuroethics & A.I. Ethics Lab at the University of Freiburg, has several concerns. High among them is identity.

In personalised decision making, evidence is required to determine suitable actions for individuals. Such evidence can be obtained by identifying treatment effect heterogeneity in different subgroups of the population. In this paper, we design a new type of pattern, treatment effect pattern to represent and discover treatment effect heterogeneity from data for determining whether a treatment will work for an individual or not. Our purpose is to use the computational power to find the most specific and relevant conditions for individuals with respect to a treatment or an action to assist with personalised decision making. Most existing work on identifying treatment effect heterogeneity takes a top-down or partitioning based approach to search for subgroups with heterogeneous treatment effects. We propose a bottom-up generalisation algorithm to obtain the most specific patterns that fit individual circumstances the best for personalised decision making. For the generalisation, we follow a consistency driven strategy to maintain inner-group homogeneity and inter-group heterogeneity of treatment effects. We also employ graphical causal modelling technique to identify adjustment variables for reliable treatment effect pattern discovery. Our method can find the treatment effect patterns reliably as validated by the experiments. The method is faster than the two existing machine learning methods for heterogeneous treatment effect identification and it produces subgroups with higher inner-group treatment effect homogeneity.

The pressure is on for companies and governments to address the ways that artificial intelligence (AI) is altering the future of work. In this video, recorded at the Aspen Ideas Festival in June, experts--Markle Foundation CEO and president Zoë Baird; Joy Buolamwini, founder of the Algorithmic Justice League at MIT Media Lab; James Fallows, national correspondent of the Atlantic; and Coursera cofounder Andrew Ng--discuss how to make the transition into this new age easier for everyone. Andrew Ng: AI is the new electricity. About 100 years ago, we started rolling out electricity in the United States, and it changed every single major industry, everything ranging from healthcare and culture to transportation, communications, and manufacturing are now all electricity powered. We now see a surprisingly clear path for AI to also transform every single major industry.

As artificial intelligence alters work done in all manner of industries, companies and governments can help workers transition by supporting incomes and facilitating skills training. The pressure is on for companies and governments to address the ways that artificial intelligence (AI) is altering the future of work. In this video, recorded at the Aspen Ideas Festival in June, experts--Markle Foundation CEO and president Zoë Baird; Joy Buolamwini, founder of the Algorithmic Justice League at MIT Media Lab; James Fallows, national correspondent of the Atlantic; and Coursera cofounder Andrew Ng--discuss how to make the transition into this new age easier for everyone. Andrew Ng: AI is the new electricity. About 100 years ago, we started rolling out electricity in the United States, and it changed every single major industry, everything ranging from healthcare and culture to transportation, communications, and manufacturing are now all electricity powered.

NEC Corporation has launched a new software program that uses artificial intelligence (AI) in video footage search to quickly identify a person by facial recognition. NeoFace Image Data Mining (Idm) is a new product offering from NEC that can use video footage, for example, data gathered by CCTV cameras, and scan it to accurately identify an individual whose image is captured on camera. It can also be used to search for people who appear at a certain time and place, or who appear with other specified individuals. A complete search for a specific person among one million captured images can be concluded in under 10 seconds. Idm combines existing facial recognition technology with profiling parameters – what NEC refers to as'Profiling Across Spatio-Temporal Data' technology.

In the first post of our non-technical ML intro series we discussed some general characteristics of ML tasks. In this post we take a first baby step towards understanding how learning algorithms work. We'll continue the dialog between an ML expert and an ML-curious person. Ok I see that an ML program can improve its performance at some task after being trained on a sufficiently large amount of data, without explicit instructions given by a human. Let's start with an extremely simple example.