#### Adaptive PCA for Time-Varying Data

In this paper, we present an online adaptive PCA algorithm that is able to compute the full dimensional eigenspace per new time-step of sequential data. The algorithm is based on a one-step update rule that considers all second order correlations between previous samples and the new time-step. Our …

#### Learning from lions: inferring the utility of agents from their trajectories

We build a model using Gaussian processes to infer a spatio-temporal vector field from observed agent trajectories. Significant landmarks or influence points in agent surroundings are jointly derived through vector calculus operations that indicate presence of sources and sinks. We evaluate these i…

#### A Deep Reinforcement Learning Chatbot

language Reinforcement Learning speech text

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ense…

#### Feature selection in high-dimensional dataset using MapReduce

This paper describes a distributed MapReduce implementation of the minimum Redundancy Maximum Relevance algorithm, a popular feature selection method in bioinformatics and network inference problems. The proposed approach handles both tall/narrow and wide/short datasets. We further provide an open …

#### Representation Learning for Visual-Relational Knowledge Graphs

Much progress has been made towards the goal of developing ML systems that are able to recognize and interpret visual scenes. With this paper, we propose query answering in visual-relational knowledge graphs (KGs) as a novel and important reasoning problem. A visual-relational KG is a KG whose enti…

#### Basic Filters for Convolutional Neural Networks: Training or Design?

audio Convolutional Neural Network

When convolutional neural networks are used to tackle learning problems based on time series, e.g., audio data, raw one-dimensional data are commonly pre-processed to obtain spectrogram or mel-spectrogram coefficients, which are then used as input to the actual neural network. In this contribution,…

#### RNN-based Early Cyber-Attack Detection for the Tennessee Eastman Process

An RNN-based forecasting approach is used to early detect anomalies in industrial multivariate time series data from a simulated Tennessee Eastman Process (TEP) with many cyber-attacks. This work continues a previously proposed LSTM-based approach to the fault detection in simpler data. It is consi…

#### Rational coordination with no communication or conventions

We study pure coordination games where in every outcome, all players have identical payoffs, ‘win’ or ‘lose’. We identify and discuss a range of ‘purely rational principles’ guiding the reasoning of rational players in such games and analyze which classes of coor…

#### Overcoming Catastrophic Forgetting by Incremental Moment Matching

Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task. Here, we propose incremental moment matching (IMM) to resolve this problem. IMM incrementally matches the moment of the posterior distribution of neural networks, whi…

#### Learning to Attend, Copy, and Generate for Session-Based Query Suggestion

Users try to articulate their complex information needs during search sessions by reformulating their queries. To make this process more effective, search engines provide related queries to help users in specifying the information need in their search process. In this paper, we propose a customized…

#### Approximating meta-heuristics with homotopic recurrent neural networks

Much combinatorial optimisation problems constitute a non-polynomial (NP) hard optimisation problem, i.e., they can not be solved in polynomial time. One such problem is finding the shortest route between two nodes on a graph. Meta-heuristic algorithms such as $A^{*}$ along with mixed-integer progr…

#### Self-Normalizing Neural Networks

Convolutional Neural Network DNN image language RNN Support Vector Machine

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNNs) are rare. FNNs that perform well are typically shallow a…

#### Bayesian Optimisation for Safe Navigation under Localisation Uncertainty

In outdoor environments, mobile robots are required to navigate through terrain with varying characteristics, some of which might significantly affect the integrity of the platform. Ideally, the robot should be able to identify areas that are safe for navigation based on its own percepts about the …

#### Interacting Attention-gated Recurrent Networks for Recommendation

Capturing the temporal dynamics of user preferences over items is important for recommendation. Existing methods mainly assume that all time steps in user-item interaction history are equally relevant to recommendation, which however does not apply in real-world scenarios where user-item interactio…

#### Machine Learning Friendly Set Version of Johnson-Lindenstrauss Lemma

In this paper we make a novel use of the Johnson-Lindenstrauss Lemma. The Lemma has an existential form saying that there exists a JL transformation $f$ of the data points into lower dimensional space such that all of them fall into predefined error range $delta$. We formulate in this paper a theor…

#### Proceedings First Workshop on Formal Verification of Autonomous Vehicles

These are the proceedings of the workshop on Formal Verification of Autonomous Vehicles, held on September 19th, 2017 in Turin, Italy, as an affiliated workshop of the International Conference on integrated Formal Methods (iFM 2017). The workshop aim is to bring together researchers from the formal…

#### Integrating Specialized Classifiers Based on Continuous Time Markov Chain

Specialized classifiers, namely those dedicated to a subset of classes, are often adopted in real-world recognition systems. However, integrating such classifiers is nontrivial. Existing methods, e.g. weighted average, usually implicitly assume that all constituents of an ensemble cover the same se…

#### Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors

Human activity recognition (HAR) has become a popular topic in research because of its wide application. With the development of deep learning, new ideas have appeared to address HAR problems. Here, a deep network architecture using residual bidirectional long short-term memory (LSTM) cells is prop…

#### Two-Timescale Stochastic Approximation Convergence Rates with Applications to Reinforcement Learning

Two-timescale Stochastic Approximation (SA) algorithms are widely used in Reinforcement Learning (RL). Their iterates have two parts that are updated with distinct stepsizes. In this work we provide a recipe for analyzing two-timescale SA. Using it, we develop the first convergence rate result for …

#### Using Posters to Recommend Anime and Mangas in a Cold-Start Scenario

Item cold-start is a classical issue in recommender systems that affects anime and manga recommendations as well. This problem can be framed as follows: how to predict whether a user will like a manga that received few ratings from the community? Content-based techniques can alleviate this issue bu…

#### Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs

This paper presents an approach to formalizing and enforcing a class of use privacy properties in data-driven systems. In contrast to prior work, we focus on use restrictions on proxies (i.e. strong predictors) of protected information types. Our definition relates proxy use to intermediate computa…

#### Sharp Bounds for Generalized Uniformity Testing

We study the problem of generalized uniformity testing cite{BC17} of a discrete probability distribution: Given samples from a probability distribution $p$ over an {em unknown} discrete domain $mathbf{Omega}$, we want to distinguish, with probability at least $2/3$, between the case that $p$ is uni…

#### Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification

DNN Generative Adversarial Network image speech

Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks (GANs) in a variety of image processing tasks, we explore …

#### A deep generative model for gene expression profiles from single-cell RNA sequencing

We propose a probabilistic model for interpreting gene expression levels that are observed through single-cell RNA sequencing. In the model, each cell has a low-dimensional latent representation. Additional latent variables account for technical effects that may erroneously set some observations of…

#### Formulation of Deep Reinforcement Learning Architecture Toward Autonomous Driving for On-Ramp Merge

ads car DQN LSTM Reinforcement Learning RNN

Multiple automakers have in development or in production automated driving systems (ADS) that offer freeway-pilot functions. This type of ADS is typically limited to restricted-access freeways only, that is, the transition from manual to automated modes takes place only after the ramp merging proce…