In 2012, artificial intelligence researchers revealed a big improvement in computers' ability to recognize images by feeding a neural network millions of labeled images from a database called ImageNet. It ushered in an exciting phase for computer vision, as it became clear that a model trained using ImageNet could help tackle all sorts of image-recognition problems. Six years later, that's helped pave the way for self-driving cars to navigate city streets and Facebook to automatically tag people in your photos. In other arenas of AI research, like understanding language, similar models have proved elusive. But recent research from fast.ai,

From 2012 to 2016, the New York City Police Department supplied IBM with thousands of surveillance images of unaware New Yorkers for the development of software that could help track down people'of interest,' a shocking report claims. IBM's technology was designed to match stills of individuals with specific physical characteristics, including clothing color, age, gender, hair color, and even skin tone, according to The Intercept. Internal documents and sources involved with the program cited by the report reveal IBM released an early iteration of its video analytics software by 2013, before improving its capabilities over the following years. The report adds to growing concerns on the potential for racial profiling with advanced surveillance technology. From 2012 to 2016, the New York City Police Department supplied IBM with thousands of surveillance images of unaware New Yorkers for the development of software that could help track down people'of interest,' a shocking report claims According to the investigation by The Intercept and the Investigative Fund, the NYPD did not end up using IBM's analytics program as part of its larger surveillance system, and discontinued it by 2016.

Feature selection can efficiently identify the most informative features with respect to the target feature used in training. However, state-of-the-art vector-based methods are unable to encapsulate the relationships between feature samples into the feature selection process, thus leading to significant information loss. To address this problem, we propose a new graph-based structurally interacting elastic net method for feature selection. Specifically, we commence by constructing feature graphs that can incorporate pairwise relationship between samples. With the feature graphs to hand, we propose a new information theoretic criterion to measure the joint relevance of different pairwise feature combinations with respect to the target feature graph representation. This measure is used to obtain a structural interaction matrix where the elements represent the proposed information theoretic measure between feature pairs. We then formulate a new optimization model through the combination of the structural interaction matrix and an elastic net regression model for the feature subset selection problem. This allows us to a) preserve the information of the original vectorial space, b) remedy the information loss of the original feature space caused by using graph representation, and c) promote a sparse solution and also encourage correlated features to be selected. Because the proposed optimization problem is non-convex, we develop an efficient alternating direction multiplier method (ADMM) to locate the optimal solutions. Extensive experiments on various datasets demonstrate the effectiveness of the proposed method. Keywords: Feature Selection; Graph; Interacting Elastic Net; Sparse; ADMM 1. Introduction There has recently been a rapid growth in both the size and dimension of the data encountered in many real world applications of pattern recognition including image processing, bioinformatics, and financial analysis. Finding useful information and building effective prediction models from such data presents new challenges for machine learning and pattern recognition [1]. One way to overcome this problem is to develop efficient spectral methods including stochastic neighbour embedding [2], elastic embedding methods [3] and feature selection [4] methods to reduce the dimensionality of the data.

A conceptually simple way to recognize images is to directly compare test-set data and training-set data. The accuracy of this approach is limited by the method of comparison used, and by the extent to which the training-set data covers the required configuration space. Here we show that this coverage can be substantially increased using simple strategies of coarse graining (replacing groups of images by their centroids) and sampling (using distinct sets of centroids in combination). We use the MNIST data set to show that coarse graining can be used to convert a subset of training images into about an order of magnitude fewer image centroids, with no loss of accuracy of classification of test-set images by direct (nearest-neighbor) classification. Distinct batches of centroids can be used in combination as a means of sampling configuration space, and can classify test-set data more accurately than can the unaltered training set. The approach works most naturally with multiple processors in parallel.

Complex systems, such as airplanes, cars, or financial markets, produce multivariate time series data consisting of system observations over a period of time. Such data can be interpreted as a sequence of segments, where each segment is associated with a certain state of the system. An important problem in this domain is to identify repeated sequences of states, known as motifs. Such motifs correspond to complex behaviors that capture common sequences of state transitions. For example, a motif of "making a turn" might manifest in sensor data as a sequence of states: slowing down, turning the wheel, and then speeding back up. However, discovering these motifs is challenging, because the individual states are unknown and need to be learned from the noisy time series. Simultaneously, the time series also needs to be precisely segmented and each segment needs to be associated with a state. Here we develop context-aware segmentation and clustering (CASC), a method for discovering common motifs in time series data. We formulate the problem of motif discovery as a large optimization problem, which we then solve using a greedy alternating minimization-based approach. CASC performs well in the presence of noise in the input data and is scalable to very large datasets. Furthermore, CASC leverages common motifs to more robustly segment the time series and assign segments to states. Experiments on synthetic data show that CASC outperforms state-of-the-art baselines by up to 38.2%, and two case studies demonstrate how our approach discovers insightful motifs in real-world time series data.

You don't need always need to build fancy algorithms to tamper with image recognition systems, adding objects in random places will do the trick. In most cases, adversarial models are used to change a few pixels here and there to distort images so objects are incorrectly recognized. A few examples have included stickers that turn images of bananas into toasters, or wearing silly glasses to be fool facial recognition systems into believing you're someone else. Let's not forget the classic case of when a turtle was mistaken as a rifle to really drill home how easy it is to outwit AI. Now researchers from the York University and the University of Toronto, Canada, however, have shown that it's possible to mislead neural networks by copying and pasting pictures of objects into images, too.

In this blog post, I am going to unfold some reasonably technical ideas pertinent most directly to the fourth point in the list: How to make meta-learning work in reality, in the context of a complex multi-algorithm cognitive architecture carrying out a variety of complicated tasks. Dr. Nil Geisweiller has recently written a research blog post describing his current work on "probabilistic inference meta-learning." In his research, he discusses using OpenCog's Probabilistic Logic Networks (PLN) framework as the base-level algorithm for meta-learning, via using pattern-mining and then PLN itself to learn patterns in large sets of PLN inference examples, to learn what sorts of inferences work better in what contexts. This gets at the crux of the meta-learning problem in an OpenCog context; it is about using PLN to help PLN learn how to reason better. This blog post is complementary to Dr. Nil's, in this post I am going to describe some work currently underway to, in effect, fuse various learning/reasoning algorithms now working separately within OpenCog so that they appear as aspects of a single unified learning/reasoning algorithm. This sort of unification provides greater elegance than a situation where there are multiple markedly distinct learning/reasoning algorithms.

Uber director of product Jairam Ranganathan says the ride-hailing company is exploring the use of artificial intelligence to create an assistive onboarding guide for prospective drivers. "Right now, a lot of this is done through documentation, things that we write, things that we send to them, but we would love to have a much more high-touch experience where people can actually talk to somebody and guide them through the process," Ranganathan said. "To do that effectively, we believe we need AI to really drive that forward, so that's one area where we definitely want to invest in going forward." He noted that Uber is already using image recognition to scan drivers' licenses and the documents necessary to onboard a new driver. Ranganathan spoke onstage today during the second day of Transform, an AI-focused event held by VentureBeat in Mill Valley, California.

Have you ever used Bing to search on the Internet? Most of us haven't but it is the rival service to Google's own search engine and it is owned and operated by none other than Microsoft. While not the most robust search engine around, obviously, Bing nonetheless has a few quirks that make it worth checking out from time to time. And you can't fault Microsoft for trying – from throwing in voice-powered Cortana search to integrating Bing into the Xbox and Windows, Microsoft has pulled out all the stops to make sure you at least have the ability to use Bing, even if you don't. Well it seems like some of us in the photography world might want to give Bing another look as Microsoft announced plans to bring powerful, artificial intelligence-powered image search to Bing.

Detecting small sets of relevant patterns from a given dataset is a central challenge in data mining. The relevance of a pattern is based on user-provided criteria; typically, all patterns that satisfy certain criteria are considered relevant. Rule-based languages like Answer Set Programming (ASP) seem well-suited for specifying such criteria in a form of constraints. Although progress has been made, on the one hand, on solving individual mining problems and, on the other hand, developing generic mining systems, the existing methods either focus on scalability or on generality. In this paper we make steps towards combining local (frequency, size, cost) and global (various condensed representations like maximal, closed, skyline) constraints in a generic and efficient way. We present a hybrid approach for itemset, sequence and graph mining which exploits dedicated highly optimized mining systems to detect frequent patterns and then filters the results using declarative ASP. To further demonstrate the generic nature of our hybrid framework we apply it to a problem of approximately tiling a database. Experiments on real-world datasets show the effectiveness of the proposed method and computational gains for itemset, sequence and graph mining, as well as approximate tiling.