Piotr Mirowski

New York University, Computer Science, Graduate Student

Followers

Following

Co-author

Public Views

I am a Staff Research Scientist working at DeepMind. As a member of the Deep Learning department and Dr. Raia Hadsell‘s team, I have been focusing on navigation-related research, in scaling up autonomous agents to real world environments and in weather forecasting
Supervisors: Yann LeCun
Address: http://cs.nyu.edu/~mirowski

less

Tufts University

United International University

Md Mahabub Mia

Bangladesh University of Engineering & Technology

Awwal Arigi

Zixuan Zhou

Tokyo Institute of Technology

Angelo Arleo

Sorbonne University

Rushi Bhatt

InterestsView All (18)

Uploads

Papers by Piotr Mirowski

Vector-based navigation using grid-like representations in artificial agents

Nature, 2018

Deep neural networks have achieved impressive successes in fields ranging from object recognition... more Deep neural networks have achieved impressive successes in fields ranging from object recognition to complex games such as Go. Navigation, however, remains a substantial challenge for artificial agents, with deep neural networks trained by reinforcement learning failing to rival the proficiency of mammalian spatial behaviour, which is underpinned by grid cells in the entorhinal cortex . Grid cells are thought to provide a multi-scale periodic representation that functions as a metric for coding space and is critical for integrating self-motion (path integration) and planning direct trajectories to goals (vector-based navigation). Here we set out to leverage the computational functions of grid cells to develop a deep reinforcement learning agent with mammal-like navigational abilities. We first trained a recurrent network to perform path integration, leading to the emergence of representations resembling grid cells, as well as other entorhinal cell types . We then showed that this re...

Download

Dependency Recurrent Neural Language Models for Sentence Completion

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 2015

Recent work on language modelling has shifted focus from count-based models to neural models. In ... more Recent work on language modelling has shifted focus from count-based models to neural models. In these works, the words in each sentence are always considered in a left-to-right order. In this paper we show how we can improve the performance of the recurrent neural network (RNN) language model by incorporating the syntactic dependencies of a sentence, which have the effect of bringing relevant contexts closer to the word being predicted. We evaluate our approach on the Microsoft Research Sentence Completion Challenge and show that the dependency RNN proposed improves over the RNN by about 10 points in accuracy. Furthermore, we achieve results comparable with the stateof-the-art models on this task.

Download

GRN code and dataset for the Genome Biology article

SignalSLAM: Simultaneous localization and mapping with mixed WiFi, Bluetooth, LTE and magnetic signals

International Conference on Indoor Positioning and Indoor Navigation, 2013

Indoor localization typically relies on measuring a collection of RF signals, such as Received Si... more Indoor localization typically relies on measuring a collection of RF signals, such as Received Signal Strength (RSS) from WiFi, in conjunction with spatial maps of signal fingerprints. A new technology for localization could arise with the use of 4G LTE telephony small cells, with limited range but with rich signal strength information, namely Reference Signal Received Power (RSRP). In this paper, we propose to combine an ensemble of available sources of RF signals to build multi-modal signal maps that can be used for localization or for network deployment optimization. We primarily rely on Simultaneous Localization and Mapping (SLAM), which provides a solution to the challenge of building a map of observations without knowing the location of the observer. SLAM has recently been extended to incorporate signal strength from WiFi in the so-called WiFi-SLAM. In parallel to WiFi-SLAM, other localization algorithms have been developed that exploit the inertial motion sensors and a known map of either WiFi RSS or of magnetic field magnitude. In our study, we use all the measurements that can be acquired by an off-the-shelf smartphone and crowd-source the data collection from several experimenters walking freely through a building, collecting time-stamped WiFi and Bluetooth RSS, 4G LTE RSRP, magnetic field magnitude, GPS reference points when outdoors, Near-Field Communication (NFC) readings at specific landmarks and pedestrian dead reckoning based on inertial data. We resolve the location of all the users using a modified version of Graph-SLAM optimization of the users poses with a collection of absolute location and pairwise constraints that incorporates multi-modal signal similarity. We demonstrate that we can recover the user positions and thus simultaneously generate dense signal maps for each WiFi access point and 4G LTE small cell, "from the pocket". Finally, we demonstrate the localization performance using selected single modalities, such as only WiFi and the WiFi signal maps that we generated.

Download

Building Optimal Radio-Frequency Signal Maps

2014 22nd International Conference on Pattern Recognition, 2014

A popular way for using radio-frequency (RF) signals (e.g. WiFi) to position people or device ind... more A popular way for using radio-frequency (RF) signals (e.g. WiFi) to position people or device indoors is by matching received radio signal strength (RSS) to fingerprints that are spatial signatures of such measures. Traditionally such signal maps are built by manual collection of repeated measurements at predefined locations following a spatial sampling scheme. Recently, such labor intensive processes are being replaced by robotbased automation or crowd-sourced simultaneous localization and mapping (SLAM). These new approaches produce timestamped trajectories along with time-stamped RSS as the human or robot moves freely about the building. However, they require an additional procedure to segment the continuous RF samples into fingerprint cells to produce a robust signal map. In this paper, we explore several strategies for building optimal signal maps from RSS collected along robotic or pedestrian trajectories. We compare two clustering algorithms with a baseline strategy that divides the trajectories into a hierarchy of fixed-size grids. We study the trade-off between the spatial extent of the fingerprint cells and the differentiability of the RSS distribution in each cell, as well as their impact on localization accuracy and on fingerprint storage. We experimented with traces collected by an autonomous robot exploring a large multi-floor office building.

Download

Prediction and analysis of ictal dynamics using computational neural networks

Characterization of epileptogenic networks in tuberous sclerosis using independent component analysis

Effects of the subdural application of lidocaine on EEG spiking in patients with focal epilepsy

Analysis of ictal dynamics using generative neural networks

Seizure Prediction Using Machine Learning on Bivariate Features from Eeg

Localization Systems and Methods

Evidence for increased neuronal electrophysiological activity before EEG seizure onset in the rat neocortical seizure focus

Pose Invariant Activity Classification for Multi-floor Indoor Localization

2014 22nd International Conference on Pattern Recognition, 2014

Smartphone based indoor localization caught massive interest of the localization community in rec... more Smartphone based indoor localization caught massive interest of the localization community in recent years. Combining pedestrian dead reckoning obtained using the phone's inertial sensors with the GraphSLAM (Simultaneous Localization and Mapping) algorithm is one of the most effective approaches to reconstruct the entire pedestrian trajectory given a set of visited landmarks during movement. A key to GraphSLAMbased localization is the detection of reliable landmarks, which are typically identified using visual cues or via NFC tags or QR codes. Alternatively, human activity can be classified to detect organic landmarks such as visits to stairs and elevators while in movement. We provide a novel human activity classification framework that is invariant to the pose of the smartphone. Pose invariant features allow robust observation no matter how a user puts the phone in the pocket. In addition, activity classification obtained by an SVM (Support Vector Machine) is used in a Bayesian framework with an HMM (Hidden Markov Model) that improves the activity inference based on temporal smoothness. Furthermore, the HMM jointly infers activity and floor information, thus providing multi-floor indoor localization. Our experiments show that the proposed framework detects landmarks accurately and enables multi-floor indoor localization from the pocket using GraphSLAM.

Download

Demand Forecasting in Smart Grids

Bell Labs Technical Journal, 2014

ABSTRACT Data analytics in smart grids can be leveraged to channel the data downpour from individ... more ABSTRACT Data analytics in smart grids can be leveraged to channel the data downpour from individual meters into knowledge valuable to electric power utilities and end-consumers. Short-term load forecasting (STLF) can address issues vital to a utility but it has traditionally been done mostly at system (city or country) level. In this case study, we exploit rich, multi-year, and high-frequency annotated data collected via a metering infrastructure to perform STLF on aggregates of power meters in a mid-sized city. For smart meter aggregates complemented with geo-specific weather data, we benchmark several state-of-the-art forecasting algorithms, including kernel methods for nonlinear regression, seasonal and temperature-adjusted auto-regressive models, exponential smoothing and state-space models. We show how STLF accuracy improves at larger meter aggregation (at feeder, substation, and system-wide level). We provide an overview of our algorithms for load prediction and discuss system performance issues that impact real time STLF. ® 2014 Alcatel-Lucent.

Probabilistic Radio-Frequency Fingerprinting and Localization on the Run

by Dimitrios Milioris and Piotr Mirowski

Bell Labs Technical Journal, 2014

Indoor localization is a key enabler for pervasive computing and network optimization. Wireless l... more Indoor localization is a key enabler for pervasive computing and network optimization. Wireless local area network (WLAN) positioning systems typically rely on fi ngerprints of received signal strength (RSS) measures from access points. In this paper, we review approaches for modeling full distributions of Wi-Fi signals, including Bayesian graphical models, smoothing, compressive sensing, and random fi eld differentiation and concentrate on the Kullback-Leibler divergence metric that compares multivariate RSS distributions. We provide theoretical insights on the required spatial density of fi ngerprints and on the number of samples necessary, during tracking or during signal map building, to differentiate among signal distributions and to provide accurate location estimates. We validate our methods on contrasting datasets where we obtain state-of-theart localization results. Finally, we exploit datasets collected by a selflocalizing mobile robot that continuously records Wi-Fi along with ground truth position, where we defi ne increasingly denser fi ngerprint grids and study asymptotic localization accuracy. © 2014 Alcatel-Lucent.

Download

SYSTEM AND METHOD FOR FEATURE-RICH CONTINUOUS SPACE LANGUAGE MODELS

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for pre... more Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size.

System and method for inferring geological classes

Illllllllllllllllllllllllllllllllllllllllllllllllln US007433851B2 (12) United States Patent ao) P... more Illllllllllllllllllllllllllllllllllllllllllllllllln US007433851B2 (12) United States Patent ao) Patent no.: us 7,433,851 B2 Mirowski (45) Date of Patent: Oct. 7,2008 (54) SYSTEM AND METHOD FOR INFERRING GEOLOGICAL CLASSES (75) Inventor: Piotr Mirowski, New York, NY (US) (73) Assignee: Schlumberger Technology Corporation, Ridgefield, CT (US) ( * ) Notice: Subject to any disclaimer, the term of this patent is extended or adjusted under 35 USC 154(b) by 4 days. (21) Appl.No.: (22) PCT Filed: (86) PCT No.: § 371 (c)(1), (2), (4) Date: 10/538,961 Jan.

METHOD, SYSTEM, AND COMPUTER-ACCESSIBLE MEDIUM FOR CLASSIFICATION OF AT LEAST ONE ICTAL STATE

An exemplary methodology, procedure, system, method and computer-accessible medium can be provide... more An exemplary methodology, procedure, system, method and computer-accessible medium can be provided for receiving physiological data for the subject, extracting one or more patterns of features from the physiological data, and classifying the at least one state of the subject using a spatial structure and a temporal structure of the one or more patterns of features, wherein at least one of the at least one state is an ictal state.

COMPUTER-BASED GENERATION AND VALIDATION OF TRAINING IMAGES FOR MULTIPOINT GEOSTATISTICAL ANALYSIS

Abstract: A computer-implemented method is provided that automatically characterizes and verifies... more Abstract: A computer-implemented method is provided that automatically characterizes and verifies stationarity of a training image for use in multipoint geostatistical analysis. The stationarity is preferably characterized by statistical measures of orientation stationarity, scale stationarity, and category distribution stationarity.

Detecting abnormally large-amplitude multi-neuron bursts before focal neocortical EEG seizure onset in freely behaving rats

Vector-based navigation using grid-like representations in artificial agents

Nature, 2018

Download

Dependency Recurrent Neural Language Models for Sentence Completion

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 2015

Download

GRN code and dataset for the Genome Biology article

SignalSLAM: Simultaneous localization and mapping with mixed WiFi, Bluetooth, LTE and magnetic signals

International Conference on Indoor Positioning and Indoor Navigation, 2013

Download

Building Optimal Radio-Frequency Signal Maps

2014 22nd International Conference on Pattern Recognition, 2014

Download

Prediction and analysis of ictal dynamics using computational neural networks

Characterization of epileptogenic networks in tuberous sclerosis using independent component analysis

Effects of the subdural application of lidocaine on EEG spiking in patients with focal epilepsy

Analysis of ictal dynamics using generative neural networks