Memory management is a decades-old research area24 that is fundamental to the performance of all applications. On modern architectures, memory managers determine a workload's ability to use 2MB (and 1GB) huge pages instead of traditional 4KB pages. The use of huge pages is crucial for performance on modern servers since they substantially reduce the cost of address translation by producing a wider reach in Translation Lookaside Buffers (TLB), reducing misses on the CPU's critical path.5 Current huge page-aware memory managers13 trade-off huge page usage with memory utilization, breaking up huge pages when they become inefficient. Figure 1 visualizes the source of this trade-off: When a C program allocates memory, it calls into a memory allocator library (e.g., TCMalloc13), which places the object at a particular address in memory until the program deletes it. The object may not move.

Spotted: According to the UN, the Earth's population will likely reach 8.5 billion by 2030. At the same time, climate change is going to make it more difficult to grow food, requiring a rapid and collaborative approach to the global food industry. For startup, The Live Green Company, the answer can be found in plants. The company has developed a way to use biotechnology and machine learning to replace animal, synthetic, and ultra-processed foods with precise plant-based alternatives. Live Green's platform, dubbed Charaka, uses machine learning to analyse data about thousands of plants and find appropriate plant substitutes for animal-based and artificial ingredients.

The reconstruction of electrical impedance tomography is a non-linear and ill-posed inverse issue. As a consequence of the non-linearity, the computing cost of a method is high, and regularisation and the most relevant observations must be utilized to minimize ill-posedness. Study: Machine learning enhanced electrical impedance tomography for 2D materials. In an article published in the journal Inverse Problems, a machine learning adaptive electrode selection technique was used to build and apply a unique approach to measurement enhancement. Altogether, this study showed how electrical impedance tomography (EIT) might be used for 2D materials and emphasized the importance of machine learning in both the numerical and computational components of electrical impedance tomography.

In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.

With all the hype around artificial intelligence, many of our customers are asking for some proof that AI can get them better results in areas where other kinds of analytics are already in use, such as credit risk assessment. With 25 years of experience with AI and machine learning under our belt, we can certainly provide that proof. My colleague Scott Zoldi blogged recently about how we use AI to build credit risk models. In this post, I'd like to drill into one of the examples he gave, to show some of the explorations we're doing to make sure we get the full power of machine learning without losing the transparency that's important in the credit risk arena. A traditional credit risk scorecard model generates a score reflecting probability of default, using various customer characteristics as inputs to the model.

Fluctuations in the cryptocurrency market is seen by some people as a sign of instability, therefore they feel that the crypto ecosystem is unpredictable and should be avoided. For most traders and speculators, this is the best mood of the market because huge swings also means increased opportunities to make profit. Trading cryptocurrencies can be great, but it can also go really fast from an informed investment practice to pure gambling. The huge profit making opportunities that are exposed by the price swings and volatility in the crypto market seems to attract a lot of new entrants, thereby causing a boom in a making that is also growing in complexity. The growing complex nature of this market has given rise to more in depth measures as traders try to find ways to sustain the consistency of winning trades.

Eric Colson, Chief Algorithms Officer at Stitch Fix, presented at FirstMark's Data Driven NYC on March 16, 2016. Colson discussed the benefits of combining machine learning and humans for better recommendations. Stitch Fix is a personal styling platform that delivers curated and personalized apparel and accessory items of perfect fit.

We present a new application and covering number bound for the framework of "Machine Learning with Operational Costs (MLOC)," which is an exploratory form of decision theory. The MLOC framework incorporates knowledge about how a predictive model will be used for a subsequent task, thus combining machine learning with the decision that is made afterwards. In this work, we use the MLOC framework to study a problem that has implications for power grid reliability and maintenance, called the Machine Learning and Traveling Repairman Problem ML&TRP. The goal of the ML&TRP is to determine a route for a "repair crew," which repairs nodes on a graph. The repair crew aims to minimize the cost of failures at the nodes, but as in many real situations, the failure probabilities are not known and must be estimated. The MLOC framework allows us to understand how this uncertainty influences the repair route. We also present new covering number generalization bounds for the MLOC framework.

Mach Learn manuscript No. (will be inserted by the editor) Abstract We present a new application and covering number bound for the framework of "Machine Learning with Operational Costs (MLOC)," which is an exploratory form of decision theory. The MLOC framework incorporates knowledge about how a predictive model will be used for a subsequent task, thus combining machine learning with the decision that is made afterwards. In this work, we use the MLOC framework to study a problem that has implications for power grid reliability and maintenance, called the Machine Learning and Traveling Repairman Problem (ML&TRP). The goal of the ML&TRP is to determine a route for a "repair crew," which repairs nodes on a graph. The repair crew aims to minimize the cost of failures at the nodes, but as in many real situations, the failure probabilities are not known and must be estimated. The MLOC framework allows us to understand how this uncertainty influences the repair route. Keywords decision theory · generalization bound · constrained linear function classes · covering numbers · traveling repairman · mixed-integer programming 1 Introduction In many domains, it is essential to understand how uncertainty in predictions influences decision-making. Funding for Theja Tulabandhula was provided by a Fulbright Fellowship and Xerox Fellowship. Cynthia Rudin's work on this project was funded in part by Con Edison, by the MIT Energy Initiative Seed Fund, and NSF grant IIS-1053407. The new framework of Machine Learning with Operational Costs (MLOC) (Tulabandhula and Rudin, 2013) provides a mechanism to do this, and is a type of exploratory decision theory. Where usual decision theories provide a single policy that minimizes expected costs, the MLOC framework is able to produce a range of reasonable policies that span the full set of reasonable costs. To do this, the operational cost becomes a regularization term within the machine learning model, and adjusting the regularization constant allows us to explore solutions for all reasonable costs. This gives decision makers a way to understand the uncertainty in their predictive model in terms of something they can grasp - uncertainty in the cost to solve the problem. The MLOC framework can also be used in another way, namely to incorporate prior knowledge about the cost to produce a better predictive model.

One of the main research problems in Structural Bioinformatics is the analysis and prediction of three-dimensional structures (3-D) of polypeptides or proteins. The 1990’s Genome projects resulted in a large increase in the number of protein sequences. However, the number of identified 3-D protein structures has not followed the same trend.The determination of protein structure is experimentally expensive and time consuming. This makes scientists largely dependent on computational methods that can predict correct 3-D protein structures only from extended and full amino acid sequences. Several computational methodologies and algorithms have been proposed as a solution to the Protein Structure Prediction (PSP) problem. We briefly describe the AI techniques we have been used to tackle this problem.