If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem domain. However, this is often not how models are trained and used in practice. For example, labels and demographics (sensitive attributes) are often hard to observe, resulting in auxiliary or synthetic data to be used for training, and proxies of the sensitive attribute to be used for evaluation of fairness. A model trained for one setting may be picked up and used in many others, particularly as is common with pre-training and cloud APIs. Despite the pervasiveness of these complexities, remarkably little work in the fairness literature has theoretically examined these issues. We frame all of these settings as domain adaptation problems: how can we use what we have learned in a source domain to debias in a new target domain, without directly debiasing on the target domain as if it is a completely new problem? We offer new theoretical guarantees of improving fairness across domains, and offer a modeling approach to transfer to data-sparse target domains. We give empirical results validating the theory and showing that these modeling approaches can improve fairness metrics with less data.

Machine Learning based Quality of Experience (QoE) models potentially suffer from over-fitting due to limitations including low data volume, and limited participant profiles. This prevents models from becoming generic. Consequently, these trained models may under-perform when tested outside the experimented population. One reason for the limited datasets, which we refer in this paper as small QoE data lakes, is due to the fact that often these datasets potentially contain user sensitive information and are only collected throughout expensive user studies with special user consent. Thus, sharing of datasets amongst researchers is often not allowed. In recent years, privacy preserving machine learning models have become important and so have techniques that enable model training without sharing datasets but instead relying on secure communication protocols. Following this trend, in this paper, we present Round-Robin based Collaborative Machine Learning model training, where the model is trained in a sequential manner amongst the collaborated partner nodes. We benchmark this work using our customized Federated Learning mechanism as well as conventional Centralized and Isolated Learning methods.

Histopathology image analysis can be considered as a Multiple instance learning (MIL) problem, where the whole slide histopathology image (WSI) is regarded as a bag of instances (i.e., patches) and the task is to predict a single class label to the WSI. However, in many reallife applications such as computational pathology, discovering the key instances that trigger the bag label is of great interest because it provides reasons for the decision made by the system. In this paper, we propose a deep convolutional neural network (CNN) model that addresses the primary task of a bag classification on a histopathology image and also learns to identify the response of each instance to provide interpretable results to the final prediction. We incorporate the attention mechanism into the proposed model to operate the transformation of instances and learn attention weights to allow us to find key patches. To perform a balanced training, we introduce adaptive weighing in each training bag to explicitly adjust the weight distribution in order to concentrate more on the contribution of hard samples. Based on the learned attention weights, we further develop a solution to boost the classification performance by generating the bags with hard negative instances. We conduct extensive experiments on colon and breast cancer histopathology data and show that our framework achieves state-of-the-art performance.

This article summarizes the lessons learned after two years of our team engaging with dozens of enterprise clients from different industries including manufacturing, financial services, retail, entertainment, and healthcare, among others. What are the most common ML problems faced by the enterprise? What is beyond training an ML model? How to address data preparation? How to scale to large datasets?

Autism Spectrum Disorder (ASD) is a developmental disorder that often impairs a child's normal development of the brain. According to CDC, it is estimated that 1 in 6 children in the US suffer from development disorders, and 1 in 68 children in the US suffer from ASD. This condition has a negative impact on a person's ability to hear, socialize and communicate. Overall, ASD has a broad range of symptoms and severity; hence the term spectrum is used. One of the main contributors to ASD is known to be genetics. Up to date, no suitable cure for ASD has been found. Early diagnosis is crucial for the long-term treatment of ASD, but this is challenging due to the lack of a proper objective measures. Subjective measures often take more time, resources, and have false positives or false negatives. There is a need for efficient objective measures that can help in diagnosing this disease early as possible with less effort. EEG measures the electric signals of the brain via electrodes placed on various places on the scalp. These signals can be used to study complex neuropsychiatric issues. Studies have shown that EEG has the potential to be used as a biomarker for various neurological conditions including ASD. This chapter will outline the usage of EEG measurement for the classification of ASD using machine learning algorithms.

The hedonic approach based on a regression model has been widely adopted for the prediction of real estate property price and rent. In particular, a spatial regression technique called Kriging, a method of interpolation that was advanced in the field of spatial statistics, are known to enable high accuracy prediction in light of the spatial dependence of real estate property data. Meanwhile, there has been a rapid increase in machine learning-based prediction using a large (big) dataset and its effectiveness has been demonstrated in previous studies. However, no studies have ever shown the extent to which predictive accuracy differs for Kriging and machine learning techniques using big data. Thus, this study compares the predictive accuracy of apartment rent price in Japan between the nearest neighbor Gaussian processes (NNGP) model, which enables application of Kriging to big data, and the deep neural network (DNN), a representative machine learning technique, with a particular focus on the data sample size (n = 10^4, 10^5, 10^6) and differences in predictive performance. Our analysis showed that, with an increase in sample size, the out-of-sample predictive accuracy of DNN approached that of NNGP and they were nearly equal on the order of n = 10^6. Furthermore, it is suggested that, for both higher and lower end properties whose rent price deviates from the median, DNN may have a higher predictive accuracy than that of NNGP.

Statistical Learning is the process of estimating an unknown probabilistic input-output relationship of a system using a limited number of observations; and a statistical learning machine (SLM) is the machine that learned such a process. While their roots grow deeply in Probability Theory, SLMs are ubiquitous in the modern world. Automatic Target Recognition (ATR) in military applications, Computer Aided Diagnosis (CAD) in medical imaging, DNA microarrays in Genomics, Optical Character Recognition (OCR), Speech Recognition (SR), spam email filtering, stock market prediction, etc., are few examples and applications for SLM; diverse fields but one theory. The field of Statistical Learning can be decomposed to two basic subfields, Design and Assessment. Three main groups of specializations-namely statisticians, engineers, and computer scientists (ordered ascendingly by programming capabilities and descendingly by mathematical rigor)-exist on the venue of this field and each takes its elephant bite. Exaggerated rigorous analysis of statisticians sometimes deprives them from considering new ML techniques and methods that, yet, have no "complete" mathematical theory. On the other hand, immoderate add-hoc simulations of computer scientists sometimes derive them towards unjustified and immature results. A prudent approach is needed that has the enough flexibility to utilize simulations and trials and errors without sacrificing any rigor. If this prudent attitude is necessary for this field it is necessary, as well, in other fields of Engineering.

First, before I start, I want to say something about what that is, or what I understand from this. So, here is one interpretation. It is about using data, obviously. So, it has relationships to analytics and data science, and it is, obviously, part of AI in some way. This is my little taxonomy, how I see things linking together. You have computer science, and that has subfields like AI, software engineering, and machine learning is typically considered to be subfield of AI, but a lot of principles of software engineering apply in this area. This is what I want to talk about today. It's heavily used in data science. So, the difference between AI and data science is somewhat fluid if you like, but data science tries to understand what's in data and tries to understand questions about data. But then it tries to use this to make decisions, and then we are back at AI, artificial intelligence, where it's mostly about automating decision making. We have a couple of definitions. AI means using intelligence, making machines intelligent, and that means you can somehow function appropriate in an environment with foresight. Machine learning is a field that looks for algorithms that can automatically improve their performance without explicit programming, but by observing relevant data. And yes, I've thrown in data science as well for good measure, the scientific process of turning data into insight for making better decisions. If you have opened any newspaper, you must have seen the discussion around the ethical dimensions of artificial intelligence, machine learning or data science. Testing touches on that as well because there are quite a few problems in that space, and I'm just listing two here. So, you use data, obviously, to do machine learning. Where does this data come from, and are you allowed to use it? Do you violate any privacy laws, or are you building models that you use to make decisions about people? If you do that, then the general data protection regulation in the EU says you have to be able to explain to an individual if you're making a decision based on an algorithm or a machine, if this decision is of any kind of significant impact. That means, in machine learning, a lot of models are already out of the door because you can't do that. You can't explain why a certain decision comes out of a machine learning model if you use particular models.

If you attended last year's RSA conference, you may have left with the idea that all you needed to build a complete cyber-security solution was a machine learning engine (or better yet, "advanced next-gen Artificial Intelligence"). Every cyber-security company uses machine learning (or AI) because it is a powerful technique for malware analysis. But it is by no means the only one. Applied naïvely, it may not even work effectively. Sometimes, a powerful scanning engine is all that is required (it's'cheap'), or even just a great database of known malware hashes (it's fast).

In LMMS has two useful properties: 1) uses contextual particular, it focuses on polysemous words which word embeddings to produce sense embeddings, have been hard to represent as embeddings due and 2) covers a large set of over 117K to the meaning conflation deficiency (Camacho-senses from WordNet 3.0. The first property allows Collados and Pilehvar, 2018). The task's objective for comparing precomputed sense embeddings is to detect if target words occurring in a pair of against contextual word embeddings generated sentences carry the same meaning.