Disciplines such as artificial intelligence and machine learning are playing increasingly important role in cyber security, but not at the expense of human intellect. This is one of the key messages from the first day of McAfee MPOWER, the company's annual security conference in Las Vegas. Indeed, one of the company's two new product launches, Investigator, has this complementary approach of human and machine at its very heart. "I think cyber security is a fundamentally different field to many other areas where artificial intelligence, machine learning is being used, Grobman said. "The example I like to give is weather forecasting [because] as we get better at forecasting weather, the laws of physics don't get upset and decide to change the way water evaporates.
From The Terminator to Blade Runner, pop culture has always leaned towards a chilling depiction of artificial intelligence (AI) and our future with AI at the helm. Recent headlines about Facebook panicking because their AI bots developed a language of their own have us hitting the alarm button once again. Should we really feel unsettled with an AI future? News flash: that future is here. If you ask Siri, the helpful assistant who magically lives inside your phone, to read text messages and emails to you, find the nearest pizza place or call your mother for you, then you've made AI a part of your everyday life.
Machine Learning can react, perhaps quickly, but is limited to past observations in development of forecasts. We cannot travel back into the past and generate another set of data so we're limited with to the single historical data set, and we are forced to devise a clever approach to making the most out of badly weakened position. The value is in the ability to quickly compare between multiple approaches and in having the ability to handle large historical data sets. Machine Learning is not limited by assumptions of consistent data generation processes--like traditional forecasting techniques.
However, businesses are exploring ways to leverage AI into their supply chain planning process including demand forecasting, production planning, and logistics planning. Streamlined Process in Supply Chain Planning The businesses relying on mechanical ways of handling their supply chain planning process are facing consequences of a tedious distribution management systems that handles multiple operations prone to human error. AI systems would be able to scan through colossal amounts of historical data to streamline every aspect of supply chain planning from demand to inventory to supply. Handle Supply Chain Disruptions Supply chain professionals are humans after all, and humans tend to stick to things that are familiar to them.
The researchers used SWAN to generate training data for the deep-learning network, feeding SWAN wave conditions from the NOAA National Data Buoy Center, live ocean current readings, and wind data from IBM-owned The Weather Company. That higher performance allows the model to create real-time forecasts of wave conditions and run simulations on hardware as small as a Raspberry Pi. As with any AI project, researchers need a lot of labeled data to train the deep-learning network. The deep-learning model can create real-time forecasts of wave conditions and run simulations on hardware as small as a Raspberry Pi.
In cybersecurity, models generally don't understand the concept of "a cyber-attack" or "malicious content," but they can do a remarkable job of fighting it by being trained on the massive quantities of data we have related to those issues. Nate Silver's best seller The Signal and the Noise (2012) notes an interesting trend suggesting that while our weather forecasting models have improved, combining this technology with human knowledge of how weather systems work has improved forecast accuracy by 25 percent. Thunderstorms are not trying to evade the latest in machine learning detection technologies -- but cyber criminals are. Whether it's threat intelligence analysis, attack reconstruction, or orchestration -- human-machine teaming takes the machine assessment of new intelligence and layers upon it the human intellect that only a human can bring.
We use the physics-based Simulating WAves Nearshore (SWAN) model to generate training data for the deep learning network. Outputs from SWAN and the deep learning network were compared to observed buoy wave data within the model domain demonstrating that despite the huge reduction in computational expense, the new approach provides comparable levels of accuracy to the traditional physics-based, SWAN model. Prof. Scott James from Baylor, who has extensive industry experience in wave forecasting applications, specifically for wave energy, joined the IBM Dublin Research Lab for a summer sabbatical to further an existing research collaboration. Together, the blend of modelling skills, machine learning capabilities and industry experience from the three institutions resulted in innovative deep learning solutions to enable wave forecasting at a fraction of the computational cost of current state-of-the-art methods.
In this multi-part blog, we first discuss Time series applications and then discuss how RNNs could apply to Time series applications. In this article (Part One), we present the overall thought process behind the use of Recurrent neural networks and Time series applications - especially a type of RNN called Long Short Term Memory networks (LSTMs). This feature of using internal memory to process arbitrary sequences of inputs makes RNNs applicable to tasks such as unsegmented connected handwriting recognition, where they have achieved the best known results. Using the same idea as time delays as above, the recurrent neural network can be converted into a traditional feed forward neural network by unfolding over time as shown below.
Salesforce thinks it has found a way to improve forecasting accuracy in its Einstein Sales Cloud product with everyone's go-to tool of late, artificial intelligence. Einstein Forecasting "allows business leaders, sales leaders, to be able to make company decisions because you have predictive information at hand," she said. The technology uses 24 months of trailing sales data to model current sales pipelines for both individual sales representatives and teams, and surfaces that through a dashboard that lets managers detect budding problems before the last two weeks of the quarter. Forecasting is part of Sales Cloud Einstein in Salesforce's flagship customer-relationship management product.
Salesforce's Einstein artificial intelligence platform celebrates its one-year anniversary this week and the CRM giant is marking the occasion with the launch of several new features. "Now, equipped with predictive and intelligent capabilities, Sales Cloud Einstein has cracked the traditionally flawed forecasting model, bringing AI to every step of the sales cycle." Salesforce also announced the launch of a $50 venture million fund that will invest in startups focused on artificial intelligence. The fund is via Salesforce Ventures and it will encourage companies to build AI capabilities on the Salesforce platform, thereby making Einstein more powerful.