AMAlejandro Molina

Alejandro Molina

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Alejandro Molina has a total of 43 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Next2You: Robust Copresence Detection Based on Channel State Information

    by Mikhail Fomichev, Luis F. Abanto-Leon, Max Stiegler, Alejandro Molina, Jakob Link, Matthias Hollick

    Context-based copresence detection schemes are a necessary prerequisite to building secure and usable authentication systems in theInternet of Things (IoT). Such schemes allow one device to verify proximity of another device without user assistance utilizing their physical context (e.g., audio). The state-of-the-art copresence detection schemes suffer from two major limitations: (1) They cannot accurately detect copresence in low-entropy context (e.g., empty room with few events occurring) and insufficiently separated environments (e.g., adjacent rooms), (2) They require devices to have common sensors (e.g., microphones) to capture context, making them impractical on devices with heterogeneous sensors. We address these limitations, proposingNext2You, a novel copresence detection scheme utilizing channel state information (CSI). In particular, we leverage magnitude and phase values from a range of subcarriers specifying a Wi-Fi channel to capture a robust wireless context created when devices communicate. We implementNext2Youon off-the-shelf smartphones relying only on ubiquitous Wi-Fi chipsets and evaluate it based on over 95 hours of CSI measurements that we collect in five real-world scenarios.Next2Youachieves error rates below 4%, maintaining accurate copresence detection both in low-entropy context and insufficiently separated environments. We also demonstrate the capability ofNext2Youto work reliably in real-time and its robustness to various attacks.


  • Open Access

    Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks

    by Alejandro Molina, Patrick Schramowski, Kristian Kersting

    The performance of deep network learning strongly depends on the choice of the non-linear activation function associated with each neuron. However, deciding on the best activation is non-trivial, and the choice depends on the architecture, hyper-parameters, and even on the dataset. Typically these activations are fixed by hand before training. Here, we demonstrate how to eliminate the reliance on first picking fixed activation functions by using flexible parametric rational functions instead. The resulting Pad\'e Activation Units (PAUs) can both approximate common activation functions and also learn new ones while providing compact representations. Our empirical evidence shows that end-to-end learning deep networks with PAUs can increase the predictive performance. Moreover, PAUs pave the way to approximations with provable robustness. https://github.com/ml-research/pau


  • Resource-Efficient Logarithmic Number Scale Arithmetic for SPN Inference on FPGAs

    by Lukas Weber, Lukas Sommer, Julian Oppermann, Alejandro Molina, Kristian Kersting, Andreas Koch

    FPGAs have been successfully used for the implementation of dedicated accelerators for a wide range of machine learning problems. The inference in so-called Sum-Product Networks can also be accelerated efficiently using a pipelined FPGA architecture. However, as Sum-Product Networks compute exact probability values, the required arithmetic precision poses different challenges than those encountered with Neural Networks. In previous work, this precision was maintained by using double-precision floating-point number formats, which are expensive to implement in FPGAs. In this work, we propose the use of a logarithmic number system format tailored specifically towards the inference in Sum-Product Networks. The evaluation of our optimized arithmetic hardware operators shows that the use of logarithmic number formats allows to save up to 50% hardware resources compared to double-precision floating point, while maintaining sufficient precision for SPN inference at almost identical performance.


  • Gaussian Lifted Marginal Filtering

    by Stefan Lüdtke, Alejandro Molina, Kristian Kersting, Thomas Kirste

  • Automatic Bayesian Density Analysis

    by Antonio Vergari, Alejandro Molina, Robert Peharz, Zoubin Ghahramani, Kristian Kersting, Isabel Valera

    Making sense of a dataset in an automatic and unsupervised fashion is a challenging problem in statistics and AI. Classical approaches for exploratory data analysis are usually not flexible enough to deal with the uncertainty inherent to real-world data: they are often restricted to fixed latent interaction models and homogeneous likelihoods; they are sensitive to missing, corrupt and anomalous data; moreover, their expressiveness generally comes at the price of intractable inference. As a result, supervision from statisticians is usually needed to find the right model for the data. However, since domain experts are not necessarily also experts in statistics, we propose Automatic Bayesian Density Analysis (ABDA) to make exploratory data analysis accessible at large. Specifically, ABDA allows for automatic and efficient missing value estimation, statistical data type and likelihood discovery, anomaly detection and dependency structure mining, on top of providing accurate density estimation. Extensive empirical evidence shows that ABDA is a suitable tool for automatic exploratory analysis of mixed continuous and discrete tabular data.


  • Open Access

    Perils of Zero-Interaction Security in the Internet of Things

    by Mikhail Fomichev, Max Maass, Lars Almon, Alejandro Molina, Matthias Hollick

    The Internet of Things (IoT) demands authentication systems which can provide both security and usability. Recent research utilizes the rich sensing capabilities of smart devices to build security schemes operating without human interaction, such as zero-interaction pairing (ZIP) and zero-interaction authentication (ZIA). Prior work proposed a number of ZIP and ZIA schemes and reported promising results. However, those schemes were often evaluated under conditions which do not reflect realistic IoT scenarios. In addition, drawing any comparison among the existing schemes is impossible due to the lack of a common public dataset and unavailability of scheme implementations. In this paper, we address these challenges by conducting the first large-scale comparative study of ZIP and ZIA schemes, carried out under realistic conditions. We collect and release the most comprehensive dataset in the domain to date, containing over 4250 hours of audio recordings and 1 billion sensor readings from three different scenarios, and evaluate five state-of-the-art schemes based on these data. Our study reveals that the effectiveness of the existing proposals is highly dependent on the scenario they are used in. In particular, we show that these schemes are subject to error rates between 0.6% and 52.8%.


  • Open Access

    SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks

    by Alejandro Molina, Antonio Vergari, Karl Stelzner, Robert Peharz, Pranav Subramani, Nicola Di Mauro, Pascal Poupart, Kristian Kersting

    We introduce SPFlow, an open-source Python library providing a simple interface to inference, learning and manipulation routines for deep and tractable probabilistic models called Sum-Product Networks (SPNs). The library allows one to quickly create SPNs both from data and through a domain specific language (DSL). It efficiently implements several probabilistic inference routines like computing marginals, conditionals and (approximate) most probable explanations (MPEs) along with sampling as well as utilities for serializing, plotting and structure statistics on an SPN. Moreover, many of the algorithms proposed in the literature to learn the structure and parameters of SPNs are readily available in SPFlow. Furthermore, SPFlow is extremely extensible and customizable, allowing users to promptly distill new inference and learning routines by injecting custom code into a lightweight functional-oriented API framework. This is achieved in SPFlow by keeping an internal Python representation of the graph structure that also enables practical compilation of an SPN into a TensorFlow graph, C, CUDA or FPGA custom code, significantly speeding-up computations.


  • Automatic Mapping of the Sum-Product Network Inference Problem to FPGA-Based Accelerators

    by Lukas Sommer, Julian Oppermann, Alejandro Molina, Carsten Binnig, Kristian Kersting, Andreas Koch

    In recent years, FPGAs have been successfully employed for the implementation of efficient, application-specific accelerators for a wide range of machine learning tasks. In this work, we consider probabilistic models, namely, (Mixed) Sum-Product Networks (SPN), a deep architecture that can provide tractable inference for multivariate distributions over mixed data-sources. We develop a fully pipelined FPGA accelerator architecture, including a pipelined interface to external memory, for the inference in (mixed) SPNs. To meet the precision constraints of SPNs, all computations are conducted using double-precision floating point arithmetic. Starting from an input description, the custom FPGA-accelerator is synthesized fully automatically by our tool flow. To the best of our knowledge, this work is the first approach to offload the SPN inference problem to FPGA-based accelerators. Our evaluation shows that the SPN inference problem benefits from offloading to our pipelined FPGA accelerator architecture.


  • Öffentlichkeitsorientierung von Wissenschaftsinstitutionen und Wissenschaftsdisziplinen

    by Julia Serong, Lars Koppers, Edith Luschmann, Alejandro Molina Ramirez, Kristian Kersting, Jörg Rahnenführer, Holger Wormer


  • Traffic Simulations with Empirical Data: How to Replace Missing Traffic Flows?

    by Lars Habel, Alejandro Molina, Thomas Zaksek, Kristian Kersting, Michael Schreckenberg