Machine Learning (ML) techniques are used by most data-driven organisations to extract insights. Machine-learning-as-a-service (MLaaS), where models are trained on potentially sensitive user data and then queried by external parties are becoming a reality. However, recently, these systems have been shown to be vulnerable to Membership Inference Attacks (MIA), where a target's data can be inferred to belong or not to the training data. While the key factors for the success of MIA have not been fully understood, existing defence mechanisms only consider the model-specific properties. We investigate the impact of both the data and ML model properties on the vulnerability of ML techniques to MIA. Our analysis indicates a strong relationship between the MIA success and the properties of the data in use, such as the data size and balance between the classes as well as the model properties including the fairness in prediction and the mutual information between the records and the model's parameters. We then propose new approaches to protect ML models from MIA by using several properties, e.g. the model's fairness and mutual information between the records and the model's parameters as regularizers, which reduces the attack accuracy by 25%, while yielding a fairer and a better performing ML model.

Algorithms that tackle deep exploration -- an important challenge in reinforcement learning -- have relied on epistemic uncertainty representation through ensembles or other hypermodels, exploration bonuses, or visitation count distributions. An open question is whether deep exploration can be achieved by an incremental reinforcement learning algorithm that tracks a single point estimate, without additional complexity required to account for epistemic uncertainty. We answer this question in the affirmative. In particular, we develop Langevin DQN, a variation of DQN that differs only in perturbing parameter updates with Gaussian noise, and demonstrate through a computational study that the algorithm achieves deep exploration. We also provide an intuition for why Langevin DQN performs deep exploration.

To make decisions based on a model fit by Auto-Encoding Variational Bayes (AEVB), practitioners typically use importance sampling to estimate a functional of the posterior distribution. The variational distribution found by AEVB serves as the proposal distribution for importance sampling. However, this proposal distribution may give unreliable (high variance) importance sampling estimates, thus leading to poor decisions. We explore how changing the objective function for learning the variational distribution, while continuing to learn the generative model based on the ELBO, affects the quality of downstream decisions. For a particular model, we characterize the error of importance sampling as a function of posterior variance and show that proposal distributions learned with evidence upper bounds are better. Motivated by these theoretical results, we propose a novel variant of the VAE. In addition to experimenting with MNIST, we present a full-fledged application of the proposed method to single-cell RNA sequencing. In this challenging instance of multiple hypothesis testing, the proposed method surpasses the current state of the art.

The principle of compositionality, which enables natural language to represent complex concepts via a structured combination of simpler ones, allows us to convey an open-ended set of messages using a limited vocabulary. If compositionality is indeed a natural property of language, we may expect it to appear in communication protocols that are created by neural agents in language games. In this paper, we propose an effective neural iterated learning (NIL) algorithm that, when applied to interacting neural agents, facilitates the emergence of a more structured type of language. Indeed, these languages provide learning speed advantages to neural agents during training, which can be incrementally amplified via NIL. We provide a probabilistic model of NIL and an explanation of why the advantage of compositional language exist. Our experiments confirm our analysis, and also demonstrate that the emerged languages largely improve the generalizing power of the neural agent communication.

Here on Codementor I usually see lots of students and developers trying to get into Machine Learning confused with complicated topics they are facing at the very beginning of their journey. I want to make a deep yet understandable introduction to the algorithm which is so simple and elegant that you would like it. If you are a Machine Learning engineer but have a limited understanding of this one, it could be also useful to read it. I was working as a software developer for years and everyone around me was talking about this brand new data science and machine learning thing (I understood that there is nothing new on this planet later), so I've decided to take masters studies in the University to get known to it. Our first module was a general introductory course to Data Science and I remember myself sitting and trying to understand what's going on.

Finally, you need to have practical experience. Nothing better than connecting with a community that has the same interests as you. You can also face competitions. Most of this answer comes from a previous answers 1 and 2 that I gave to this (Brazilian) site. I must have forgotten lots of great references... Sorry about that.

In the previous article, we studied Multiple Linear Regression. One thing that I believe is that if we can correlate anything with us or our lives, there are greater chances of understanding the concept. So I will try to explain everything by relating it to humans. A decision tree is a decision support tool that uses a tree-like graph or model of decisions and their possible consequences, including chance event outcomes, resource costs, and utility. It is one way to display an algorithm that only contains conditional control statements.

Machine learning shows great performance in various problems of electrocardiography (ECG) signal analysis. However, collecting a dataset for biomedical engineering is a very difficult task. Any dataset for ECG processing contains from 100 to 10,000 times fewer cases than datasets for image or text analysis. This issue is especially important because of physiological phenomena that can significantly change the morphology of heartbeats in ECG signals. In this preliminary study, we analyze the effects of lead choice from the standard ECG recordings, variation of ECG during 24-hours, and the effects of QT-prolongation agents on the performance of machine learning methods for ECG processing. We choose the problem of subject identification for analysis, because this problem may be solved for almost any available dataset of ECG data. In a discussion, we compare our findings with observations from other works that use machine learning for ECG processing with different problem statements. Our results show the importance of training dataset enrichment with ECG signals acquired in specific physiological conditions for obtaining good performance of ECG processing for real applications.

The wide variety of motions performed by the human arm during daily tasks makes it desirable to find representative subsets to reduce the dimensionality of these movements for a variety of applications, including the design and control of robotic and prosthetic devices. This paper presents a novel method and the results of an extensive human subjects study to obtain representative arm joint angle trajectories that span naturalistic motions during Activities of Daily Living (ADLs). In particular, we seek to identify sets of useful motion trajectories of the upper limb that are functions of a single variable, allowing, for instance, an entire prosthetic or robotic arm to be controlled with a single input from a user, along with a means to select between motions for different tasks. Data driven approaches are used to obtain clusters as well as representative motion averages for the full-arm 7 degree of freedom (DOF), elbow-wrist 4 DOF, and wrist-only 3 DOF motions. The proposed method makes use of well-known techniques such as dynamic time warping (DTW) to obtain a divergence measure between motion segments, DTW barycenter averaging (DBA) to obtain averages, Ward's distance criterion to build hierarchical trees, batch-DTW to simultaneously align multiple motion data, and functional principal component analysis (fPCA) to evaluate cluster variability. The clusters that emerge associate various recorded motions into primarily hand start and end location for the full-arm system, motion direction for the wrist-only system, and an intermediate between the two qualities for the elbow-wrist system. The proposed clustering methodology is justified by comparing results against alternative approaches.

Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the underlying mechanics of meta-learning and the difference between models trained using meta-learning and models which are trained classically. In doing so, we develop several hypotheses for why meta-learned models perform better. In addition to visualizations, we design several regularizers inspired by our hypotheses which improve performance on few-shot classification.