FinTech 2019: 5 uses cases of machine learning in finance

#artificialintelligence

We all know about machine learning when it comes to Japanese droids or Rhoomba intelligent vacuum cleaners, but how is machine learning being used in finance and fintech? As you will discover, the use of machine learning is both prolific and amazing. We will soon look back and wonder how we lived without machine learning. "Machine learning will automate jobs that most people thought could only be done by people." The brilliant way that machine learning has been implemented to help protect against fraud is amazing when you consider the sheer weight of staff/human time required to do the same job.


Beware! Criminals are using AI to steal your personal details - DataFlair

#artificialintelligence

With the wide use of artificial intelligence in various fields, expectations are high that it may become prevalent for attacking purposes than defensive ones. Mark Testoni, the president and CEO of an enterprise security company, SAP NS2, said that hackers and criminals are highly skeptical just like the communities that develop defense systems for themselves. The techniques that the communities use, are used by hackers such as captchas and image recognition, development of malware, phishing and whaling, and many more. They are getting aware of when to hide and attack. Criminals are covering themselves with the help of artificial intelligence, instead of covering behind masks to rob a bank.


AI Can Now Make Medical Predictions from Raw Data Through 'Deep Learning.' But Can it Be Trusted?

#artificialintelligence

Already, at Massachusetts General Hospital in Boston, "every one of the 50,000 screening mammograms we do every year is processed through our deep learning model, and that information is provided to the radiologist," says Constance Lehman, chief of the hospital's breast imaging division. In deep learning, a subset of a type of artificial intelligence called machine learning, computer models essentially teach themselves to make predictions from large sets of data. The raw power of the technology has improved dramatically in recent years, and it's now used in everything from medical diagnostics to online shopping to autonomous vehicles. But deep learning tools also raise worrying questions because they solve problems in ways that humans can't always follow. If the connection between the data you feed into the model and the output it delivers is inscrutable -- hidden inside a so-called black box -- how can it be trusted?


AIs To Compete In Minecraft Machine Learning Competition

#artificialintelligence

As reported by Nature, a new AI competition will be occurring soon, the MineRL competition, which will encourage AI engineers and coders to create programs capable of learning through observation and example. The test case for these AI systems will be the highly popular crafting and survival video game Minecraft. Artificial intelligence systems are have seen some recent impressive accomplishments when it comes to video games. Just recently an AI beat out the best human players in the world at the strategy game StarCraft II. However, StarCraft II has definable goals that are easier to break down into coherent steps that an AI can use to train.


Deep Learning Models for Automatic Seizure Detection in Epilepsy

#artificialintelligence

Cleveland Clinic is a non-profit academic medical center. Advertising on our site helps support our mission. Epilepsy is the second most common neurological disorder, impacting 1% to 2% of the world's population. Individuals with epilepsy typically undergo long-term monitoring of the brain's electrical activity with EEG recordings for several days. The recorded EEG data are manually reviewed by a trained neurologist, a neurophysiologist or a skilled EEG reader to identify epileptic seizures or interictal discharges that characterize the individual's epilepsy.


AI Model Developer ai-jobs.net

#artificialintelligence

Does quantitative modeling excite you? Are you an innovative thinker and interested in risk topics? Do you enjoy understanding algorithms and their background? We're looking for a model developer who will: • design, build and test AI models and solutions for business stakeholders and users primarily relying on Python based libraries and frameworks • ensure adherence to standards related to our AI development pipeline, model validation, front / back-end interfaces and workflow procedures • design and implement reusable Python assets, code templates and ongoing AI development framework enhancements. Methodologies and Models within Group Compliance, Regulatory and Governance is a newly established unit which uses state of the art AI/Machine Learning based solutions, covering the entire non-financial risk control and compliance space.


Gradient Estimation Using Stochastic Computation Graphs

Neural Information Processing Systems

In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external world. Estimating the gradient of this loss function, using samples, lies at the core of gradient-based learning algorithms for these problems. We introduce the formalism of stochastic computation graphs--directed acyclic graphs that include both deterministic functions and conditional probability distributions and describe how to easily and automatically derive an unbiased estimator of the loss function's gradient. The resulting algorithm for computing the gradient estimator is a simple modification of the standard backpropagation algorithm. The generic scheme we propose unifies estimators derived in variety of prior work, along with variance-reduction techniques therein.


Unified representation of tractography and diffusion-weighted MRI data using sparse multidimensional arrays

Neural Information Processing Systems

Recently, linear formulations and convex optimization methods have been proposed to predict diffusion-weighted Magnetic Resonance Imaging (dMRI) data given estimates of brain connections generated using tractography algorithms. The size of the linear models comprising such methods grows with both dMRI data and connectome resolution, and can become very large when applied to modern data. In this paper, we introduce a method to encode dMRI signals and large connectomes, i.e., those that range from hundreds of thousands to millions of fascicles (bundles of neuronal axons), by using a sparse tensor decomposition. We show that this tensor decomposition accurately approximates the Linear Fascicle Evaluation (LiFE) model, one of the recently developed linear models. We provide a theoretical analysis of the accuracy of the sparse decomposed model, LiFESD, and demonstrate that it can reduce the size of the model significantly.


The Multiple Quantile Graphical Model

Neural Information Processing Systems

We introduce the Multiple Quantile Graphical Model (MQGM), which extends the neighborhood selection approach of Meinshausen and Buhlmann for learning sparse graphical models. The latter is defined by the basic subproblem of modeling the conditional mean of one variable as a sparse function of all others. Our approach models a set of conditional quantiles of one variable as a sparse function of all others, and hence offers a much richer, more expressive class of conditional distribution estimates. We establish that, under suitable regularity conditions, the MQGM identifies the exact conditional independencies with probability tending to one as the problem size grows, even outside of the usual homoskedastic Gaussian data model. We develop an efficient algorithm for fitting the MQGM using the alternating direction method of multipliers.


Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning

Neural Information Processing Systems

Posterior sampling for reinforcement learning (PSRL) is an effective method for balancing exploration and exploitation in reinforcement learning. Randomised value functions (RVF) can be viewed as a promising approach to scaling PSRL. However, we show that most contemporary algorithms combining RVF with neural network function approximation do not possess the properties which make PSRL effective, and provably fail in sparse reward problems. Moreover, we find that propagation of uncertainty, a property of PSRL previously thought important for exploration, does not preclude this failure. We use these insights to design Successor Uncertainties (SU), a cheap and easy to implement RVF algorithm that retains key properties of PSRL.