Deep Belief Networks (DBN) and Autoencoders, Let's take a look at DBNs and how they are created on top of RBMs. If you haven't read the previous posts yet, you can read them by clicking the below links. A DBN is a network that was created to overcome a problem that existed in standard artificial neural networks. Backpropagation is a phenomenon that might result in "local minima" or "vanishing gradients." DBN is designed to solve this problem by stacking numerous RBMs.

Once in a while every data scientist needs some inspiration. Or maybe you just want to learn new things or to see what's going on in the awesome field called Machine Learning. On Github there's a lot of brilliant and well crafted ML repos. Here's just a fraction of what Github has to offer. I hope you will enjoy it and let's get started!

This work studies the question of Representation Learning in RL: how can we learn a compact low-dimensional representation such that on top of the representation we can perform RL procedures such as exploration and exploitation, in a sample efficient manner. We focus on the low-rank Markov Decision Processes (MDPs) where the transition dynamics correspond to a low-rank transition matrix. Unlike prior works that assume the representation is known (e.g., linear MDPs), here we need to learn the representation for the low-rank MDP. We study both the online RL and offline RL settings. For the online setting, operating with the same computational oracles used in FLAMBE (Agarwal et.al), the state-of-art algorithm for learning representations in low-rank MDPs, we propose an algorithm REP-UCB Upper Confidence Bound driven Representation learning for RL), which significantly improves the sample complexity from $\widetilde{O}( A^9 d^7 / (\epsilon^{10} (1-\gamma)^{22}))$ for FLAMBE to $\widetilde{O}( A^4 d^4 / (\epsilon^2 (1-\gamma)^{3}) )$ with $d$ being the rank of the transition matrix (or dimension of the ground truth representation), $A$ being the number of actions, and $\gamma$ being the discounted factor. Notably, REP-UCB is simpler than FLAMBE, as it directly balances the interplay between representation learning, exploration, and exploitation, while FLAMBE is an explore-then-commit style approach and has to perform reward-free exploration step-by-step forward in time. For the offline RL setting, we develop an algorithm that leverages pessimism to learn under a partial coverage condition: our algorithm is able to compete against any policy as long as it is covered by the offline distribution.

Trust calibration is necessary to ensure appropriate user acceptance in advanced automation technologies. A significant challenge to achieve trust calibration is to quantitatively estimate human trust in real-time. Although multiple trust models exist, these models have limited predictive performance partly due to individual differences in trust dynamics. A personalized model for each person can address this issue, but it requires a significant amount of data for each user. We present a methodology to develop customized model by clustering humans based on their trust dynamics. The clustering-based method addresses the individual differences in trust dynamics while requiring significantly less data than personalized model. We show that our clustering-based customized models not only outperform the general model based on entire population, but also outperform simple demographic factor-based customized models. Specifically, we propose that two models based on ``confident'' and ``skeptical'' group of participants, respectively, can represent the trust behavior of the population. The ``confident'' participants, as compared to the ``skeptical'' participants, have higher initial trust levels, lose trust slower when they encounter low reliability operations, and have higher trust levels during trust-repair after the low reliability operations. In summary, clustering-based customized models improve trust prediction performance for further trust calibration considerations.

Machine learning has successfully framed many sequential decision making problems as either supervised prediction, or optimal decision-making policy identification via reinforcement learning. In data-constrained offline settings, both approaches may fail as they assume fully optimal behavior or rely on exploring alternatives that may not exist. We introduce an inherently different approach that identifies possible ``dead-ends'' of a state space. We focus on the condition of patients in the intensive care unit, where a ``medical dead-end'' indicates that a patient will expire, regardless of all potential future treatment sequences. We postulate ``treatment security'' as avoiding treatments with probability proportional to their chance of leading to dead-ends, present a formal proof, and frame discovery as an RL problem. We then train three independent deep neural models for automated state construction, dead-end discovery and confirmation. Our empirical results discover that dead-ends exist in real clinical data among septic patients, and further reveal gaps between secure treatments and those that were administered.

We propose an automaton model which is a combination of symbolic and register automata, i.e., we enrich symbolic automata with memory. We call such automata Symbolic Register Automata (SRA). SRA extend the expressive power of symbolic automata, by allowing Boolean formulas to be applied not only to the last element read from the input string, but to multiple elements, stored in their registers. SRA also extend register automata, by allowing arbitrary Boolean formulas, besides equality predicates. We study the closure properties of SRA under union, intersection, concatenation, Kleene closure, complement and determinization and show that SRA, contrary to symbolic automata, are not in general closed under complement and they are not determinizable. However, they are closed under these operations when a window operator, quintessential in Complex Event Recognition, is used. We show how SRA can be used in Complex Event Recognition in order to detect patterns upon streams of events, using our framework that provides declarative and compositional semantics, and that allows for a systematic treatment of such automata. We also show how the behavior of SRA, as they consume streams of events, can be given a probabilistic description with the help of prediction suffix trees. This allows us to go one step beyond Complex Event Recognition to Complex Event Forecasting, where, besides detecting complex patterns, we can also efficiently forecast their occurrence.

We study a novel setting in Online Markov Decision Processes (OMDPs) where the loss function is chosen by a non-oblivious strategic adversary who follows a no-external regret algorithm. In this setting, we first demonstrate that MDP-Expert, an existing algorithm that works well with oblivious adversaries can still apply and achieve a policy regret bound of $\mathcal{O}(\sqrt{T \log(L)}+\tau^2\sqrt{ T \log(|A|)})$ where $L$ is the size of adversary's pure strategy set and $|A|$ denotes the size of agent's action space. Considering real-world games where the support size of a NE is small, we further propose a new algorithm: MDP-Online Oracle Expert (MDP-OOE), that achieves a policy regret bound of $\mathcal{O}(\sqrt{T\log(L)}+\tau^2\sqrt{ T k \log(k)})$ where $k$ depends only on the support size of the NE. MDP-OOE leverages the key benefit of Double Oracle in game theory and thus can solve games with prohibitively large action space. Finally, to better understand the learning dynamics of no-regret methods, under the same setting of no-external regret adversary in OMDPs, we introduce an algorithm that achieves last-round convergence result to a NE. To our best knowledge, this is first work leading to the last iteration result in OMDPs.

Most of the existing literature on supervised learning problems focuses on the case when the training data set is drawn from an i.i.d. sample. However, many practical supervised learning problems are characterized by temporal dependence and strong correlation between the marginals of the data-generating process, suggesting that the i.i.d. assumption is not always justified. This problem has been already considered in the context of Markov chains satisfying the Doeblin condition. This condition, among other things, implies that the chain is not singular in its behavior, i.e. it is irreducible. In this article, we focus on the case when the training data set is drawn from a not necessarily irreducible Markov chain. Under the assumption that the chain is uniformly ergodic with respect to the $\mathrm{L}^1$-Wasserstein distance, and certain regularity assumptions on the hypothesis class and the state space of the chain, we first obtain a uniform convergence result for the corresponding sample error, and then we conclude learnability of the approximate sample error minimization algorithm and find its generalization bounds. At the end, a relative uniform convergence result for the sample error is also discussed.

MC Dropout is a mainstream "free lunch" method in medical imaging for approximate Bayesian computations (ABC). Its appeal is to solve out-of-the-box the daunting task of ABC and uncertainty quantification in Neural Networks (NNs); to fall within the variational inference (VI) framework; and to propose a highly multimodal, faithful predictive posterior. We question the properties of MC Dropout for approximate inference, as in fact MC Dropout changes the Bayesian model; its predictive posterior assigns $0$ probability to the true model on closed-form benchmarks; the multimodality of its predictive posterior is not a property of the true predictive posterior but a design artefact. To address the need for VI on arbitrary models, we share a generic VI engine within the pytorch framework. The code includes a carefully designed implementation of structured (diagonal plus low-rank) multivariate normal variational families, and mixtures thereof. It is intended as a go-to no-free-lunch approach, addressing shortcomings of mean-field VI with an adjustable trade-off between expressivity and computational complexity.

Topic models provide a useful text-mining tool for learning, extracting and discovering latent structures in large text corpora. Although a plethora of methods have been proposed for topic modeling, a formal theoretical investigation on the statistical identifiability and accuracy of latent topic estimation is lacking in the literature. In this paper, we propose a maximum likelihood estimator (MLE) of latent topics based on a specific integrated likelihood, which is naturally connected to the concept of volume minimization in computational geometry. Theoretically, we introduce a new set of geometric conditions for topic model identifiability, which are weaker than conventional separability conditions relying on the existence of anchor words or pure topic documents. We conduct finite-sample error analysis for the proposed estimator and discuss the connection of our results with existing ones. We conclude with empirical studies on both simulated and real datasets.