Emotion recognition is a classic field of research with a typical setup extracting features and feeding them through a classifier for prediction. On the other hand, generative models jointly capture the distributional relationship between emotions and the feature profiles. Relatively recently, Generative Adversarial Networks (GANs) have surfaced as a new class of generative models and have shown considerable success in modeling distributions in the fields of computer vision and natural language understanding. In this work, we experiment with variants of GAN architectures to generate feature vectors corresponding to an emotion in two ways: (i) A generator is trained with samples from a mixture prior. Each mixture component corresponds to an emotional class and can be sampled to generate features from the corresponding emotion. (ii) A one-hot vector corresponding to an emotion can be explicitly used to generate the features. We perform analysis on such models and also propose different metrics used to measure the performance of the GAN models in their ability to generate realistic synthetic samples. Apart from evaluation on a given dataset of interest, we perform a cross-corpus study where we study the utility of the synthetic samples as additional training data in low resource conditions.

Inferring the most likely configuration for a subset of variables of a joint distribution given the remaining ones - which we refer to as co-generation - is an important challenge that is computationally demanding for all but the simplest settings. This task has received a considerable amount of attention, particularly for classical ways of modeling distributions like structured prediction. In contrast, almost nothing is known about this task when considering recently proposed techniques for modeling high-dimensional distributions, particularly generative adversarial nets (GANs). Therefore, in this paper, we study the occurring challenges for co-generation with GANs. To address those challenges we develop an annealed importance sampling based Hamiltonian Monte Carlo co-generation algorithm. The presented approach significantly outperforms classical gradient based methods on a synthetic and on the CelebA and LSUN datasets.

In this paper, we propose and analyze SPARQ-SGD, which is an event-triggered and compressed algorithm for decentralized training of large-scale machine learning models. Each node can locally compute a condition (event) which triggers a communication where quantized and sparsified local model parameters are sent. In SPARQ-SGD each node takes at least a fixed number ($H$) of local gradient steps and then checks if the model parameters have significantly changed compared to its last update; it communicates further compressed model parameters only when there is a significant change, as specified by a (design) criterion. We prove that the SPARQ-SGD converges as $O(\frac{1}{nT})$ and $O(\frac{1}{\sqrt{nT}})$ in the strongly-convex and non-convex settings, respectively, demonstrating that such aggressive compression, including event-triggered communication, model sparsification and quantization does not affect the overall convergence rate as compared to uncompressed decentralized training; thereby theoretically yielding communication efficiency for "free". We evaluate SPARQ-SGD over real datasets to demonstrate significant amount of savings in communication over the state-of-the-art.

Energy-based models (EBMs) are powerful probabilistic models, but suffer from intractable sampling and density evaluation due to the partition function. As a result, inference in EBMs relies on approximate sampling algorithms, leading to a mismatch between the model and inference. Motivated by this, we consider the sampler-induced distribution as the model of interest and maximize the likelihood of this model. This yields a class of energy-inspired models (EIMs) that incorporate learned energy functions while still providing exact samples and tractable log-likelihood lower bounds. We describe and evaluate three instantiations of such models based on truncated rejection sampling, self-normalized importance sampling, and Hamiltonian importance sampling. These models outperform or perform comparably to the recently proposed Learned Accept/Reject Sampling algorithm and provide new insights on ranking Noise Contrastive Estimation and Contrastive Predictive Coding. Moreover, EIMs allow us to generalize a recent connection between multi-sample variational lower bounds and auxiliary variable variational inference. We show how recent variational bounds can be unified with EIMs as the variational family.

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised or reinforcement learning tasks, and often assumes full knowledge of task labels and boundaries. In this work, we propose an approach (CURL) to tackle a more general problem that we will refer to as unsupervised continual learning. The focus is on learning representations without any knowledge about task identity, and we explore scenarios when there are abrupt changes between tasks, smooth transitions from one task to another, or even when the data is shuffled. The proposed approach performs task inference directly within the model, is able to dynamically expand to capture new concepts over its lifetime, and incorporates additional rehearsal-based techniques to deal with catastrophic forgetting. We demonstrate the efficacy of CURL in an unsupervised learning setting with MNIST and Omniglot, where the lack of labels ensures no information is leaked about the task. Further, we demonstrate strong performance compared to prior art in an i.i.d setting, or when adapting the technique to supervised tasks such as incremental class learning.

Purpose: Variability in patient treatment responses can be a barrier to effective care. Utilization of available patient databases may improve the prediction of treatment responses. We evaluated machine learning methods to predict novel, individual patient responses to pregabalin for painful diabetic peripheral neuropathy, utilizing an agent-based modeling and simulation platform that integrates real-world observational study (OS) data and randomized clinical trial (RCT) data. Patients and methods: The best supervised machine learning methods were selected (through literature review) and combined in a novel way for aligning patients with relevant subgroups that best enable prediction of pregabalin responses. Data were derived from a German OS of pregabalin (N 2642) and nine international RCTs (N 1320).

For example, suppose you want to build a simple linear regression model using an m-dimensional training data set. If the model uses the gradient descent algorithm to minimize the objective function in order to determine the weights w_0, w_1, w_2, …,w_m, then we can have an optimizer such as GradientDescent(eta, n_iter). Here eta (learning rate) and n_iter (number of iterations) are the hyperparameters that would have to be adjusted in order to obtain the best values for the model parameters w_0, w_1, w_2, …,w_m. For more information about this, see the following example: Machine Learning: Python Linear Regression Estimator Using Gradient Descent. Here, n_iter is the number of iterations, eta0 is the learning rate, and eed of the pseudo random number generator to use when shuffling the data.

Continuing Our series of posts on how to interpret Machine Learning algorithms and predictions. Part 0 (optional) -- What is Data Science and the Data Scientist Part 1 -- Introduction to Interpretability Part 1.5 (optional) -- A Brief History of Statistics (May be useful to understand this post) Part 2 -- (this post) Interpreting models of high bias and low variance. Part 4 -- Is it possible to resolve the trade-off between bias and variance? Using Shapley to finally open the black box! In this post we will focus on the interpretation of high bias and low variance models, as we explained in the previous post, these algorithms are the easiest to interpret so assume several prerequisites in the data.

Understanding data usually is half the battle won. For any machine learning project it helps immensely to analyze your data from different points of view. Summarising a dataset means understanding how your data looks when subjected to simple statistical anaylsis. To illustrate the various techniques let us consider the glass dataset from the r package mlbench. It has 214 observations containing examples of the chemical analysis of 7 different types of glass. For a quick look we try to display the first 10 rows of the data.

Welcome to the second stepping stone of Supervised Machine Learning. Again, this chapter is divided into two parts. Part 2 (here) we take on small coding exercise challenge. If you haven't read the Naive Bayes, I would suggest you to read it thorough here. A Support Vector Machine (SVM) is a discriminative classifier formally defined by a separating hyperplane.