Computing expected predictions has many interesting applications in areas such as fairness, handling missing values, and data analysis. Unfortunately, computing expectations of a discriminative model with respect to a probability distribution defined by an arbitrary generative model has been proven to be hard in general. In fact, the task is intractable even for simple models such as logistic regression and a naive Bayes distribution. In this paper, we identify a pair of generative and discriminative models that enables tractable computation of expectations of the latter with respect to the former, as well as moments of any order, in case of regression. Specifically, we consider expressive probabilistic circuits with certain structural constraints that support tractable probabilistic inference. Moreover, we exploit the tractable computation of high-order moments to derive an algorithm to approximate the expectations, for classification scenarios in which exact computations are intractable. We evaluate the effectiveness of our exact and approximate algorithms in handling missing data during prediction time where they prove to be competitive to standard imputation techniques on a variety of datasets. Finally, we illustrate how expected prediction framework can be used to reason about the behaviour of discriminative models.

-- Active perception strategies enable an agent to selectively gather information in a way to improve its performance. In applications in which the agent does not have prior knowledge about the available information sources, it is crucial to synthesize active perception strategies at runtime. We consider a setting in which at runtime an agent is capable of gathering information under a limited budget. We pose the problem in the context of partially observable Markov decision processes. We propose a generalized greedy strategy that selects a subset of information sources with near-optimality guarantees on uncertainty reduction. Our theoretical analysis establishes that the proposed active perception strategy achieves near-optimal performance in terms of expected cumulative reward. We demonstrate the resulting strategies in simulations on a robotic navigation problem. An intelligent system should be able to exploit the available information in its surroundings toward better accomplishment of its task.

Probability is a field of mathematics that is universally agreed to be the bedrock for machine learning. Although probability is a large field with many esoteric theories and findings, the nuts and bolts, tools and notations taken from the field are required for machine learning practitioners. With a solid foundation of what probability is, it is possible to focus on just the good or relevant parts. In this crash course, you will discover how you can get started and confidently understand and implement probabilistic methods used in machine learning with Python in seven days. This is a big and important post. You might want to bookmark it. Probability for Machine Learning (7-Day Mini-Course) Photo by Percita, some rights reserved.

This book was designed around major ideas and methods that are directly relevant to machine learning algorithms. There are a lot of things you could learn about probability, from theory to abstract concepts to APIs. My goal is to take you straight to developing an intuition for the elements you must understand with laser-focused tutorials. I designed the tutorials to focus on how to get things done with probability. They give you the tools to both rapidly understand and apply each technique or operation. Each tutorial is designed to take you less than one hour to read through and complete, excluding the extensions and further reading. You can choose to work through the lessons one per day, one per week, or at your own pace. I think momentum is critically important, and this book is intended to be read and used, not to sit idle. I would recommend picking a schedule and sticking to it.

It seems like everyone is looking to start a career in artificial intelligence and machine learning nowadays. That's no surprise when you take into account the high salaries, a multitude of available job offers, and an opportunity to work with some of the hottest companies around. You'll need to familiarize youself with popular machine learning interview questions. At the same time, the fact that a lot of people are currently interested in machine learning as a career means that there are fewer jobs to go around. If you want to stand out from the crowd, you have to ace that machine learning interview.

We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/decoder framework. Our key principles are symmetry and mutual information, where symmetry encourages the encoder and decoder to learn different factorizations of the same underlying distribution, and mutual information, to encourage the learning of useful representations for downstream tasks. Our starting point is the symmetric Jensen-Shannon divergence between the encoding and decoding joint distributions, plus a mutual information encouraging regularizer. We show that this can be bounded by a tractable cross entropy loss function between the true model and a parameterized approximation, and relate this to the maximum likelihood framework. We also relate MIM to variational autoencoders (VAEs) and demonstrate that MIM is capable of learning symmetric factorizations, with high mutual information that avoids posterior collapse.

To understand how rich dynamics emerge in neural populations, we require models which exhibit a wide range of dynamics while remaining interpretable in terms of connectivity and single-neuron dynamics. However, it has been challenging to fit such mechanistic spiking networks at the single neuron scale to empirical population data. To close this gap, we propose to fit such data at a meso scale, using a mechanistic but low-dimensional and hence statistically tractable model. The mesoscopic representation is obtained by approximating a population of neurons as multiple homogeneous `pools' of neurons, and modelling the dynamics of the aggregate population activity within each pool. We derive the likelihood of both single-neuron and connectivity parameters given this activity, which can then be used to either optimize parameters by gradient ascent on the log-likelihood, or to perform Bayesian inference using Markov Chain Monte Carlo (MCMC) sampling. We illustrate this approach using a model of generalized integrate-and-fire neurons for which mesoscopic dynamics have been previously derived, and show that both single-neuron and connectivity parameters can be recovered from simulated data. In particular, our inference method extracts posterior correlations between model parameters, which define parameter subsets able to reproduce the data. We compute the Bayesian posterior for combinations of parameters using MCMC sampling and investigate how the approximations inherent to a mesoscopic population model impact the accuracy of the inferred single-neuron parameters.

In our case, the data was provided by Safecity India, which is a platform launched on 2012, that crowdsources personal stories of sexual harassment and abuse in public spaces [2]. They have collected over 10,000 stories from over 50 cities in India, Kenya, Cameroon, and Nepal. More specifically they provided us a .cvs Additionally to the focal tasks of this project and as part of the NLP channel we decided to automate the category classification based on the sexual harassment case descriptions. Performing this classification task manually is time-consuming and leaving it entirely on the hands of the victim could produce ambiguity in the discrimination of the categories.

Meta-learning over a set of distributions can be interpreted as learning different types of parameters corresponding to short-term vs long-term aspects of the mechanisms underlying the generation of data. These are respectively captured by quickly-changing parameters and slowly-changing meta-parameters. We present a new framework for meta-learning causal models where the relationship between each variable and its parents is modeled by a neural network, modulated by structural meta-parameters which capture the overall topology of a directed graphical model. Our approach avoids a discrete search over models in favour of a continuous optimization procedure. We study a setting where interventional distributions are induced as a result of a random intervention on a single unknown variable of an unknown ground truth causal model, and the observations arising after such an intervention constitute one meta-example. To disentangle the slow-changing aspects of each conditional from the fast-changing adaptations to each intervention, we parametrize the neural network into fast parameters and slow meta-parameters. We introduce a meta-learning objective that favours solutions robust to frequent but sparse interventional distribution change, and which generalize well to previously unseen interventions. Optimizing this objective is shown experimentally to recover the structure of the causal graph.