Log messages are now widely used in software systems. They are important for classification as millions of logs are generated each day. Most logs are unstructured which makes classification a challenge. In this paper, Deep Learning (DL) methods called Auto-LSTM, Auto-BLSTM and Auto-GRU are developed for anomaly detection and log classification. These models are used to convert unstructured log data to trained features which is suitable for classification algorithms. They are evaluated using four data sets, namely BGL, Openstack, Thunderbird and IMDB. The first three are popular log data sets while the fourth is a movie review data set which is used for sentiment classification and is used here to show that the models can be generalized to other text classification tasks. The results obtained show that Auto-LSTM, Auto-BLSTM and Auto-GRU perform better than other well-known algorithms.

"This new supercomputer will enable us to mine deep databases of genomic and clinical information using machine–learning approaches to propel the …

GeoSoftware, part of CGG's Geoscience division, has announced that machine learning technology in Python ecosystems will be available in …

HackNotice Premium also taps machine learning to gives consumers personalized response recommendations.

Mitigating prejudicial and abusive behavior online is no easy feat, given the level of toxicity in some communities. More than one in five respondents in a recent survey reported being subjected to physical threats, and nearly one in five experienced sexual harassment, stalking, or sustained harassment. Of those who experienced harassment, upwards of 20% said it was the result of their gender identity, race, ethnicity, sexual orientation, religion, occupation, or disability. In pursuit of a solution, Jigsaw -- the organization working under Google parent company Alphabet to tackle cyber bullying, censorship, disinformation, and other digital issues of the day -- today released what it claims is the largest public data set of comments and annotations with toxicity labels and identity labels. It's intended to help measure bias in AI comment classification systems, which Jigsaw and others have historically measured using synthetic data from template sentences.

WITF-FM, a public radio, television, and online news broadcaster in central Pennsylvania, includes the following statement above select online news coverage: "WITF strives to provide nuanced perspectives from the most authoritative sources. We are on the lookout for biases or assumptions in our own work, and we invite you to point out any we may have missed." It's not uncommon for news organizations to invite comments and feedback from their audience; in fact, most encourage it. But WITF has gone above and beyond a general invitation for engagement. This statement highlights the potential for bias in their own reporting -- and their attempt to avoid it.

Jason Blazaikis's automated far-right propagandist knows the hits. Asked to complete the phrase "The greatest danger facing the world today," the software declared it to be "Islamo-Nazism," which it said will cause "a Holocaust on the population of Europe." The paragraph of text that followed also slurred Jews and admonished that "nations who value their peoples [sic] legends need to recognize the magnitude of the Islamic threat." Blazaikis is director of the Center on Terrorism, Extremism, and Counter-Terrorism at the Middlebury Institute of International Studies, where researchers are attempting to preview the future of online information warfare. The text came from machine learning software they had fed a collection of manifestos from right-wing terrorists and mass-murderers such as Dylann Roof and Anders Breivik.