Ali Ramezani-Kebrya
Image:
Private

Ali Ramezani-Kebrya

Visual Intelligence PI awarded prestigious research grant

Congratulations to associate professor Ali Ramezani-Kebrya for receiving a prestigious FRIPRO grant from the Research Council of Norway!

Visual Intelligence PI awarded prestigious national grant

Congratulations to associate professor Ali Ramezani-Kebrya for receiving the prestigious FRIPRO grant from the Research Council of Norway!

By Petter Bjørklund, Communications Advisor at SFI Visual Intelligence

On April 9th, the Research Council of Norway announced that he was awarded a prestigious national grant of NOK 8 million for his project Machine Learning in Real World (MLReal) through the FRIPRO programme. Ramezani-Kebrya is a principal investigator at Visual Intelligence and Integreat – Norwegian Centre for Knowledge-driven Machine Learning.

FRIPRO is a national, open-competition funding scheme designed to support bold, curiosity-driven research across all disciplines. The program aims to advance the state of the art by enabling innovative ideas from experienced researchers with a proven track record of excellence.

Machine Learning in the Real World

Machine learning (ML) with deep neural networks has made significant progress in recent years, enabling tasks like detecting anomalies in medical images and translating between less commonly studied languages. However, we are still far from reaching ML’s full potential, mainly because current learning theory doesn’t fully explain how to achieve the lowest possible error in real-world conditions. Practical tools that try to deal with real-world data often lack generality and are tailored to specific scenarios. Realistic conditions—such as limited computing power, missing data, or system failures—differ greatly from ideal lab settings. One of the key questions is how neural networks identify and extract the most relevant information from input data to make accurate predictions.

The MLReal project aims to understand and improve how neural networks process information, focusing on two key ideas: sufficiency (capturing enough information for prediction) and minimality (capturing only what’s necessary). By studying how data is transformed through different network layers using advanced mathematical tools, MLReal introduces new ways to measure and reduce prediction errors under real-world constraints.

This understanding allows the development of practical ML tools that can handle challenges across diverse fields like neuroscience, marine research, and emotion recognition—pushing the boundaries of what ML can achieve in everyday, imperfect conditions.

Ramezani-Kebrya brings extensive international experience from institutions such as EPFL and the Vector Institute, and he is an active contributor to leading AI research communities, including ELLIS, NeurIPS, and AISTATS. His research interests span from neural network theory to practical applications in emotion recognition, marine data, and neuroscience.

Latest news

Visual Intelligence represented at EAGE Annual 2025

June 15, 2025

Alba Ordoñez and Anders U. Waldeland presented ongoing work on seismic foundation models and an interactive seismic interpretation engine at EAGE Annual 2025 in Toulouse, France.

Visual Intelligence PhD Fellow Eirik Østmo featured on Abels tårn

June 13, 2025

Østmo was invited to Abels tårn—one of the largest popular science radio shows in Norway—to answer listener-submitted questions related to artificial Intelligence (AI). The live show took place at Blårock Cafe in Tromsø, Norway on June 12th.

New Industrial PhD project with Kongsberg Satellite Services

June 12, 2025

VI industry partner Kongsberg Satellite Services (KSAT) received an Industrial PhD grant from the Research Council of Norway. The project will be closely connected to Visual Intelligence's "Earth observation" innovation area.

Visual Intelligence represented at plankton-themed workshop by The Institute of Marine Research

June 11, 2025

Visual Intelligence Researchers Amund Vedal and Arnt Børre Salberg recently presented ongoing Visual Intelligence research at a plankton-themed workshop organized by the Institute of Marine Research (IMR), Norway

My Research Stay at Visual Intelligence: Teresa Dorszewski

June 5, 2025

Teresa Dorszewski is a PhD Candidate at the Section for Cognitive Systems at the Technical University of Denmark. She visited Visual Intelligence in Tromsø from January to April 2025.

Visual Intelligence represented at the NORA Annual Conference 2025

June 3, 2025

Centre Director Robert Jenssen was invited to give a keynote and participate in a panel discussion on AI as critical national infrastructure at the NORA Annual Conference 2025 in Halden, Norway.

NRK.no: Nekter å svare om umerkede puslespill er KI-generert: – De bør være ærlige

June 2, 2025

Både forskere og statsråd mener kunstig intelligens bør tydelig merkes. Men forlaget som lager puslespillet som ekspertene mener er KI-generert, sier de ikke har noe med hvordan illustratører lager produktene sine (Norwegian news article by NRK)

ScienceNorway: This is how AI can contribute to faster treatment of lung cancer

May 30, 2025

Researchers have developed an artificial intelligence to map specific immune cells in lung cancer tumors. It can lead to less costly examinations and more personalised cancer treatment (English news story on sciencenorway.no).

Now Hiring: 4 PhD Fellows in Deep Learning

May 28, 2025

The Department of Physics and Technology at UiT The Arctic University of Norway is pleased to announce 4 exciting PhD Fellowships within machine learning at SFI Visual Intelligence. Application deadline: June 17th.

VG: Slik kan AI revolusjonere lungekreftbehandling

May 19, 2025

Norsk forskning har utviklet kunstig intelligens som raskt kan analysere lungekreft. Ekspertene forklarer hvordan dette kan bidra til en mer effektiv og persontilpasset behandling (Norwegian news article in vg.no)

Visual Intelligence evaluated by international experts: "The centre operates at an excellent level"

April 29, 2025

After four years of operation, an international AI expert panel was appointed to assess Visual Intelligence's progress and results. The evaluation was characterized by its excellent remarks on the centre's scientific quality and innovation output.

Visual Intelligence at Norsk Radiografforbund's mammography symposium

April 24, 2025

Senior Researcher Fredrik Dahl recently gave a talk about Norsk Regnesentral's work on developing AI algorithms for automatic analysis of image quality and cancer detection at Norsk Radiografforbund's mammography symposium in Oslo.