Domain > www.iandewancker.com

More information on this domain is in AlienVault OTX

DNS Resolutions

Date	IP Address
2025-12-21	108.138.167.117 (ClassC)
2026-02-01	3.169.173.57 (ClassC)

HTTP/1.1 200 OKContent-Type: text/html; charsetUTF-8Content-Length: 10138Connection: keep-aliveDate: Sun, 01 Feb 2026 17:23:18 GMTETag: d2bfa03243918e0c8bc0012587f90feea3d6dd5dServer: TornadoServer/4.4.2X-Cache: Miss from cloudfrontVia: 1.1 11017c4db22106ac70e16ce75190a430.cloudfront.net (CloudFront)X-Amz-Cf-Pop: HIO52-P4X-Amz-Cf-Id: 7GaRw8VtTMQ4uDqwL3FW2rfeWp6r9kVait3xUUXX2JV_rHt1guVrqQ

style>body {margin: 50px;margin-top: 50px;margin-right: 250px;margin-bottom: 50px;margin-left: 250px;max-width: 800px;font-family: Roboto, sans-serif;margin:50px auto;}h1 {font-weight: 400;}h2 {background-color: #ddf;border-bottom: 3px solid #55a;padding: 5px 10px;margin: 1.8em 0 1em;font-weight: 400;}div.article {border-style: solid;border-color: #55a;margin-top: 25px;margin-bottom: 25px;padding-left: 15px;padding-top: 5px;passing-bottom: 10px;display: inline-block;}div.intro_article {border-color: #55a;margin-top: 25px;margin-bottom: 25px;padding-left: 15px;padding-top: 5px;passing-bottom: 10px;display: inline-block;}/style>html>header>/header>body>h1> Ian Dewancker/h1>div>p >I work as an engineer at a hrefhttps://www.kindred.ai/ target_blank>Kindred AI/a> with a focus on applied machine learning.I am particularly interested in ML applications related to interactive information retrieval, Bayesian optimization, and robotics.More generally, Im interested in the principled design, implementation, evaluationand optimization of machine learning systems./p>span>a hrefFILES/ian_dewancker_dec_2019.pdf target_blank>resume/a> |a hrefhttps://twitter.com/idewanck target_blank>twitter/a> |a hrefhttps://github.com/iandewancker target_blank>github/a> |a hrefhttps://www.linkedin.com/in/ian-dewancker-7a293625/ target_blank>linkedin/a> |a hrefhttps://www.quora.com/profile/Ian-Dewancker target_blank>quora/a>/span>/div>h2> Technical Articles/h2>!--div classarticle>Learning Preference Solicitation Policies for Personalized Item Relevance Models/div> -->div classarticle>div stylefloat:left; width:30%>div stylemargin:20px 5% 5% 5%;>img srcIMGS/motion_planning_v6.png styleheight: auto; width: 100%;>/div>/div>div stylefloat:right; width:70% >div stylemargin:0% 5% 5% 5%;>h3 stylemargin-bottom:3px;> Sequential Preference-Based Optimization/h3>a stylemargin : 0; hrefhttp://bayesiandeeplearning.org/ target_blank>i>Bayesian Deep Learning Workshop at NIPS 2017/i> /a>p>Many real-world engineering problems rely on human preferences to guide their design and optimization. PrefOpt is an open source package for simplifying sequential optimization tasks that incorporate human preference feedback. Our approach extends an existing latent variable model for binary preferences to allow for observations of equivalent preference from users./p>br>span classmenu>a hrefhttp://bayesiandeeplearning.org/2017/papers/22.pdf target_blank>pdf/a> |a hrefFILES/prefopt_poster.pdf target_blank>poster/a> |a hrefhttps://github.com/prefopt/prefopt target_blank>code/a> |a hrefFILES/Sequential_Preference-Based_Optimization.pdf target_blank>slides/a>span>/div>/div>/div>div classarticle>div stylefloat:left; width:30%>div stylemargin:20px 5% 5% 5%;>img srcIMGS/multi_obj.png styleheight: auto; width: 100%;>/div>/div>div stylefloat:right; width:70% >div stylemargin:0% 5% 5% 5%;>h3 stylemargin-bottom:3px;> Interactive Preference Learning of Utility Functions for Multi-objective Optimization/h3>a stylemargin : 0; hrefhttp://www.filmnips.com/accepted-papers/ target_blank>i>FILM Workshop at NIPS 2016/i> /a>p>For practical machine learning systems, performance tuning is often more nuanced than minimizing a single expected loss objective, and it may be more realistically discussed as a multi-objective optimization problem. We propose a novel generative model for scalar-valued utility functions to capture human preferences in a multi-objective optimization setting. We also outline an interactive active learning system that sequentially refines the understanding of stakeholders ideal utility functions using binary preference queries./p>br>span classmenu>a hrefhttps://arxiv.org/pdf/1612.04453 target_blank>pdf/a> |a hrefFILES/interactive_util_poster.pdf target_blank>poster/a> |a hrefFILES/lightning_interactive_util.pdf target_blank>slides/a>span>/div>/div>/div>div classarticle>div stylefloat:left; width:30%>div stylemargin:20px 5% 5% 5%;>img srcIMGS/practical_ml.png styleheight: auto; width: 100%;>/div>/div>div stylefloat:right; width:70% >div stylemargin:0% 5% 5% 5%;>h3> Bayesian Optimization for Machine Learning : br> A Practical Guidebook/h3>p>This guidebook was written to serve as a useful resource for machine learning practitioners looking to take advantage of Bayesian optimization techniques. We outline four example machine learning problems that can be solved using open source machine learning libraries, and highlight the benefits of using Bayesian optimization in the context of these common applications./p>br>span classmenu>a hrefhttps://arxiv.org/pdf/1612.04858 target_blank>pdf/a> |a hrefhttps://github.com/iandewancker/sigopt-examples target_blank>code/a> |a hrefhttps://www.youtube.com/watch?vCGI_RKVnDpE target_blank>video 1/a> |a hrefhttps://www.youtube.com/watch?vKzy8UPNHow4 target_blank>video 2/a>span>/div>/div>/div>div classarticle>div stylefloat:left; width:30%>div stylemargin:20px 5% 5% 5%;>img srcIMGS/bo_analysis.png styleheight: auto; width: 100%;>/div>/div>div stylefloat:right; width:70% >div stylemargin:0% 5% 5% 5%;>h3 stylemargin-bottom:3px;>Stratified Analysis of Bayesian Optimization Methods/h3>a stylemargin : 0; hrefhttps://sites.google.com/site/automl2016/accepted-papers target_blank>i>AutoML Workshop at ICML 2016 /i> /a>p>Empirical analysis serves as an important complement to theoretical analysis for studying practical Bayesian optimization. We define two metrics for comparing the performance of Bayesian optimization methods and propose a ranking mechanism for summarizing performance within various genres or strata of test functions. These test functions serve to mimic the complexity of hyperparameter optimization problems, the most prominent application of Bayesian optimization, but with a closed form which allows for rapid evaluation and more predictable behavior./p>br>span classmenu>a hrefhttps://arxiv.org/abs/1603.09441 target_blank>pdf/a> |a hrefhttps://github.com/sigopt/evalset target_blank>code/a>span>/div>/div>/div>div classarticle>div stylefloat:left; width:30%>div stylemargin:20px 5% 5% 5%;>img srcIMGS/eval_sys.png styleheight: auto; width: 100%;>/div>/div>div stylefloat:right; width:70% >div stylemargin:0% 5% 5% 5%;>h3 stylemargin-bottom:3px;> Evaluation System for a Bayesian Optimization Service/h3>a stylemargin : 0; hrefhttps://sites.google.com/site/mlsys2016/accepted-papers target_blank>i>ML Systems Workshop at ICML 2016 /i> /a>p>Bayesian optimization is an elegant solution to the hyperparameter optimization problem in machine learning. Building a reliable and robust Bayesian optimization service requires careful testing methodology and sound statistical analysis. We present an overview of our evaluation system and discuss how this framework empowers our research engineers to confidently and quickly make changes to our core optimization engine/p>br>span classmenu>a hrefhttps://arxiv.org/pdf/1605.06170 target_blank>pdf/a> |a hrefFILES/mlsys-poster-jun24.pdfi target_blank>poster/a>span>/div>/div>/div>div classarticle>div stylefloat:left; width:30%>div stylemargin:20px 5% 5% 5%;>img srcIMGS/mobisense.png styleheight: auto; width: 100%;>/div>/div>div stylefloat:right; width:70% >div stylemargin:0% 5% 5% 5%;>h3> MSc Thesis : Lifespace Tracking and Activity Monitoring on Mobile Phones /h3>p>Daily patterns of behaviour are a rich source of information and play an important role in establishing a person’s quality of life. MobiSense is a mobile health research platform that aims to improve mobility analysis for both ambulating and wheelchair users. The goals of the system were to be simple for users to collect mobility data, provide accessible summaries of daily behaviours and to enable further research and development in this area. The system is capable of lifespace summaries relating to indoor and outdoor mobility as well as activity trends and behaviours./p>br>span classmenu>a hrefhttps://open.library.ubc.ca/media/download/pdf/24/1.0166870/1 target_blank>pdf/a> |a hrefFILES/thesis_prez.pdf target_blank>slides/a>span>/div>/div>/div>h2> Projects /h2>div classarticle>div stylefloat:left; width:30%>div stylemargin:20px 5% 5% 5%;>img srcIMGS/sublexis_frame.png styleheight: auto; width: 100%;>/div>/div>div stylefloat:right; width:70% >div stylemargin:0% 5% 5% 5%;>h3> Sublexis : Language Learning through Film-based Flashcards /h3>p>Sublexis is a free tool for improving French, English and Spanish vocabulary. It presents users with chains of flashcards (taken from film scenes) as examples of word context. Its not perfect, but I find it pretty fun for learning new French words myself. Ive tried to design it to work well on mobile and touch screen devices, try it out and let me know what you think!/p>br>span classmenu>a hrefhttp://www.sublexis.com/ target_blank>site/a> |a hrefhttps://www.instagram.com/sublexis/ target_blank>instagram/a>span>/div>/div>/div>div classarticle>div stylefloat:left; width:30%>div stylemargin:20px 5% 5% 5%;>img srcIMGS/vizDAT_v1.jpg styleheight: auto; width: 100%;>/div>/div>div stylefloat:right; width:70% >div stylemargin:0% 5% 5% 5%;>h3> vizDAT : Interactive Visualizations of ML Datasets /h3>p>vizdat is an interactive visualization tool that helps users explore and understand their datasets./p>/div>/div>/div>/body>/html>

View on OTX | View on ThreatMiner

Data with thanks to AlienVault OTX, VirusTotal, Malwr and others. [Sitemap]

Domain > www.iandewancker.com

Is this malicious?

DNS Resolutions

Port 80

Port 443