<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>luca.bertinetto</title><link>https://lucabertinetto.com/</link><description>Recent content on luca.bertinetto</description><generator>Hugo</generator><language>en-gb</language><lastBuildDate>Sun, 09 Feb 2020 00:00:00 +0000</lastBuildDate><atom:link href="https://lucabertinetto.com/index.xml" rel="self" type="application/rss+xml"/><item><title>Warsaw, Poland</title><link>https://lucabertinetto.com/photos/warsaw-poland/</link><pubDate>Sun, 09 Feb 2020 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/photos/warsaw-poland/</guid><description>&lt;p&gt;&lt;a href="https://en.wikipedia.org/w/index.php?title=Palace_of_Culture_and_Science&amp;amp;oldid=945815549" class="content-link"&gt;Palace of Culture and Science&lt;/a&gt; (Polish: Pałac Kultury i Nauki), is a notable high-rise building in central Warsaw, Poland. With a total height of 237 metres (778 ft) it is the tallest building in Poland, the 5th-tallest building in the European Union (including spire) and one of the tallest on the European continent.
Constructed in 1955, it houses various public and cultural institutions such as cinemas, theatres, libraries, sports clubs, university faculties and authorities of the Polish Academy of Sciences.&lt;/p&gt;</description></item><item><title>Hel, Poland</title><link>https://lucabertinetto.com/photos/hel-poland-3/</link><pubDate>Thu, 06 Feb 2020 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/photos/hel-poland-3/</guid><description>&lt;p&gt;&lt;a href="https://en.wikipedia.org/w/index.php?title=Hel_Peninsula&amp;amp;oldid=939640541" class="content-link"&gt;Hel Peninsula&lt;/a&gt; (Polish: Mierzeja Helska) is a 35-km-long sand bar peninsula in northern Poland separating the Bay of Puck from the open Baltic Sea.
The width of the peninsula varies from approximately 300 m near Jurata, through 100 m in the most narrow part to over 3 km at the tip. Since the peninsula was formed entirely of sand, it is frequently turned into an island by winter storms. Until the 17th century the peninsula was a chain of islands that formed a strip of land only during the summer.&lt;/p&gt;</description></item><item><title>Hel, Poland</title><link>https://lucabertinetto.com/photos/hel-poland-2/</link><pubDate>Thu, 23 Jan 2020 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/photos/hel-poland-2/</guid><description>&lt;p&gt;&lt;a href="https://en.wikipedia.org/w/index.php?title=Hel_Peninsula&amp;amp;oldid=939640541" class="content-link"&gt;Hel Peninsula&lt;/a&gt; (Polish: Mierzeja Helska) is a 35-km-long sand bar peninsula in northern Poland separating the Bay of Puck from the open Baltic Sea.
The width of the peninsula varies from approximately 300 m near Jurata, through 100 m in the most narrow part to over 3 km at the tip. Since the peninsula was formed entirely of sand, it is frequently turned into an island by winter storms. Until the 17th century the peninsula was a chain of islands that formed a strip of land only during the summer.&lt;/p&gt;</description></item><item><title>Arizona, US</title><link>https://lucabertinetto.com/photos/arizona-us/</link><pubDate>Tue, 21 Jan 2020 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/photos/arizona-us/</guid><description>&lt;p&gt;The &lt;a href="https://en.wikipedia.org/w/index.php?title=Grand_Canyon&amp;amp;oldid=952699432" class="content-link"&gt;Grand Canyon&lt;/a&gt;
is a steep-sided canyon carved by the Colorado River in Arizona, United States.
The canyon is 277 miles (446 km) long, up to 18 miles (29 km) wide and attains a depth of over a mile (6,093 feet or 1,857 meters).&lt;/p&gt;</description></item><item><title>Chicago, US</title><link>https://lucabertinetto.com/photos/chicago-us/</link><pubDate>Tue, 21 Jan 2020 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/photos/chicago-us/</guid><description>&lt;p&gt;&lt;a href="https://en.wikipedia.org/w/index.php?title=Chicago&amp;amp;oldid=953376675" class="content-link"&gt;Chicago&lt;/a&gt;, officially the City of Chicago, is the most populous city in the U.S. state of Illinois, and the third-most-populous city in the United States. With an estimated population of 2,705,994 (2018), it is also the most populous city in the Midwestern United States. Chicago is the county seat of Cook County, the second-most-populous county in the US, with a small portion of the northwest side of the city extending into DuPage County near O&amp;rsquo;Hare Airport. Chicago is the principal city of the Chicago metropolitan area, often referred to as Chicagoland. At nearly 10 million people, the metropolitan area is the third most populous in the United States.&lt;/p&gt;</description></item><item><title>Panaji, India</title><link>https://lucabertinetto.com/photos/panaji-india-2/</link><pubDate>Tue, 07 Jan 2020 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/photos/panaji-india-2/</guid><description>&lt;p&gt;&lt;a href="https://en.wikipedia.org/w/index.php?title=Panaji&amp;amp;oldid=949879387" class="content-link"&gt;Panaji&lt;/a&gt;, formerly Panjim, is the capital of the Indian state of Goa and the headquarters of North Goa district. It lies on the banks of the Mandovi River estuary in the Ilhas de Goa sub-district (taluka). With a population of 114,759 in the metropolitan area, Panjim is Goa&amp;rsquo;s largest urban agglomeration, ahead of Margão and Vasco da Gama.&lt;/p&gt;</description></item><item><title>Introduction</title><link>https://lucabertinetto.com/posts/what-is-hugo/</link><pubDate>Sat, 03 Aug 2019 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/posts/what-is-hugo/</guid><description>&lt;p&gt;Hugo is an open-source project and lives by the work of its contributors. There are plenty of open issues, and we need your help to make Hugo even more awesome. You don&amp;rsquo;t need to be a Go guru to contribute to the project&amp;rsquo;s development.&lt;/p&gt;</description></item><item><title>What is Hugo</title><link>https://lucabertinetto.com/posts/introduction/</link><pubDate>Mon, 01 Jul 2019 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/posts/introduction/</guid><description>&lt;p&gt;Hugo is a fast and modern static site generator written in Go, and designed to make website creation fun again.&lt;/p&gt;</description></item><item><title>About</title><link>https://lucabertinetto.com/about/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/about/</guid><description>&lt;p&gt;Hi, and thanks for visiting my page. If you are interested in my public research, you can find a selected list of my work &lt;a href="../research" class="content-link"&gt;here&lt;/a&gt;, or on my &lt;a href="https://scholar.google.com/citations?user=zEy5CTkAAAAJ" class="content-link"&gt;Google Scholar profile&lt;/a&gt;.&lt;/p&gt;
&lt;p&gt;I am excited by AI for Science and the prospects of &amp;ldquo;autonomous&amp;rdquo; scientific discovery: systems that tighten the loop between hypothesis, experiment, and insight, not replacing scientists and engineers but allowing them to work at ever higher levels of abstraction.&lt;/p&gt;
&lt;p&gt;I am currently at &lt;a href="https://www.recursion.com" class="content-link"&gt;Recursion&lt;/a&gt; / &lt;a href="https://www.valencelabs.com" class="content-link"&gt;Valence Labs&lt;/a&gt;, where we learn models of biology from large-scale perturbation data to accelerate and improve drug discovery. My current focus is on bridging the scarce but highly informative signal from patient data with the massive scale of controlled in-vitro experiments, so that hypotheses grounded in patient biology can be exhaustively explored in-silico.
I joined Recursion through the &lt;a href="https://www.reuters.com/markets/deals/biotech-firm-recursion-buy-smaller-peer-exscientia-688-million-2024-08-08/" class="content-link"&gt;acquisition&lt;/a&gt; of Exscientia, where I led ML research in precision medicine.&lt;/p&gt;</description></item><item><title>Adversarial attacks on perception components</title><link>https://lucabertinetto.com/patents/adversarial_attacks/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/patents/adversarial_attacks/</guid><description/></item><item><title>Attacking deep networks with surrogate-based adversarial black-box methods is easy</title><link>https://lucabertinetto.com/research/blackbox_attacks/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/blackbox_attacks/</guid><description/></item><item><title>Do Different Tracking Tasks Require Different Appearance Models?</title><link>https://lucabertinetto.com/research/neurips21_tracking/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/neurips21_tracking/</guid><description/></item><item><title>Effective Biological Representation Learning by Masking Gene Expression</title><link>https://lucabertinetto.com/research/txfm/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/txfm/</guid><description/></item><item><title>End-to-end representation learning for the Correlation Filter</title><link>https://lucabertinetto.com/research/cfnet/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/cfnet/</guid><description/></item><item><title>Fast online object tracking and segmentation: A unifying approach</title><link>https://lucabertinetto.com/research/siammask/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/siammask/</guid><description/></item><item><title>Fully-convolutional siamese networks for object tracking</title><link>https://lucabertinetto.com/research/siamfc/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/siamfc/</guid><description/></item><item><title>Hierarchical Interaction Network for Video Object Segmentation from Referring Expressions</title><link>https://lucabertinetto.com/research_unused/referring_expressions/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research_unused/referring_expressions/</guid><description/></item><item><title>Learning (to learn) from few examples</title><link>https://lucabertinetto.com/research/dphil_thesis/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/dphil_thesis/</guid><description/></item><item><title>Learning feed-forward one-shot learners</title><link>https://lucabertinetto.com/research/learnet/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/learnet/</guid><description/></item><item><title>Let’s Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation</title><link>https://lucabertinetto.com/research_unused/camera_reloc/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research_unused/camera_reloc/</guid><description/></item><item><title>Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks</title><link>https://lucabertinetto.com/research/better_mistakes/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/better_mistakes/</guid><description/></item><item><title>Meta-learning with differentiable closed-form solvers</title><link>https://lucabertinetto.com/research/r2d2/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/r2d2/</guid><description/></item><item><title>On episodes, prototypical networks, and few-shot learning</title><link>https://lucabertinetto.com/research/steinar/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/steinar/</guid><description/></item><item><title>Online domain adaptation</title><link>https://lucabertinetto.com/patents/online_domain_adaptation/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/patents/online_domain_adaptation/</guid><description/></item><item><title>Parameter-free Online Test-time Adaptation</title><link>https://lucabertinetto.com/research/lame/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/lame/</guid><description/></item><item><title>Self-supervised Test-time Adaptation on Video Data</title><link>https://lucabertinetto.com/research_unused/selfsup_tta/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research_unused/selfsup_tta/</guid><description/></item><item><title>Staple: Complementary Learners for Real-Time Tracking</title><link>https://lucabertinetto.com/research/staple/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/staple/</guid><description/></item><item><title>Structure detection models</title><link>https://lucabertinetto.com/patents/structure_detection/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/patents/structure_detection/</guid><description/></item><item><title>Workshop series on Pre-registration in Machine Learning</title><link>https://lucabertinetto.com/research/preregistration/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lucabertinetto.com/research/preregistration/</guid><description/></item></channel></rss>