phd machine learning france

• Research & Faculty
• Offices & Services
• Information for:
• Faculty & Staff
• News & Events
• Contact & Visit
• About the Department
• Message from the Chair
• Computer Science Major (BS/BA)
• Computer Science Minor
• Data Science and Engineering Minor
• Combined BS (or BA)/MS Degree Program
• Intro Courses
• Special Programs & Opportunities
• Student Groups & Organizations
• Undergraduate Programs
• Undergraduate Research
• Senior Thesis
• Peer Mentors
• Curriculum & Requirements
• MS in Computer Science
• PhD in Computer Science
• Admissions FAQ
• Financial Aid
• Graduate Programs
• Courses Collapse Courses Submenu
• Research Overview
• Research Areas
• Systems and Networking
• Security and Privacy
• Programming Languages
• Artificial Intelligence
• Human-Computer Interaction
• Vision and Graphics
• Groups & Labs
• Affiliated Centers & Institutes
• Industry Partnerships
• Adobe Research Partnership
• Center for Advancing Safety of Machine Intelligence
• Submit a Tech Report
• Tech Reports
• Tenure-Track Faculty
• Faculty of Instruction
• Affiliated Faculty
• Adjunct Faculty
• Postdoctoral Fellows
• PhD Students
• Outgoing PhDs and Postdocs
• Visiting Scholars
• News Archive
• Weekly Bulletin
• Monthly Student Newsletter
• All Public Events
• Seminars, Workshops, & Talks
• Distinguished Lecture Series
• CS Colloquium Series
• CS + X Events
• Tech Talk Series
• Honors & Awards
• External Faculty Awards
• University Awards
• Department Awards
• Student Resources
• Undergraduate Student Resources
• MS Student Resources
• PhD Student Resources
• Student Organization Resources
• Faculty Resources
• Postdoc Resources
• Staff Resources
• Purchasing, Procurement and Vendor Payment
• Expense Reimbursements
• Department Operations and Facilities
• Initiatives
• Student Groups
• CS Faculty Diversity Committee
• Broadening Participation in Computing (BPC) Plan
• Northwestern Engineering

CS Senior Spotlight: Julian Baldwin

Baldwin graduates with a combined bachelor’s and master’s degree in computer science and plans to apply to phd programs in machine learning.

For Julian Baldwin , who graduates this month with a combined BS/MS degree in computer science, his Northwestern Engineering experience reinforced why he chose the field. Computer science, he said, perfectly blends his passion for math with his desire to create, build, and approach projects with a design eye.

Baldwin also served as a peer-study group leader for the Engineering Analysis sequence of the McCormick School of Engineering core curriculum for first-year students. In addition, he is a former president of Effective Altruism Northwestern , a student group that leads fellowships and discussions focused on maximizing positive impact.

We asked Baldwin, who was recently named among 12 ‘ outstanding CS seniors ’ for academic excellence and contributions to Northwestern CS, about his experiences at Northwestern Engineering, opportunities for impactful collaborations, and his advice for current students.

Why did you decide to pursue the combined BS/MS degree in computer science at McCormick?

I became interested in computer science in my last two years of high school. It combined much of what I enjoy about math — the clear logical systems and satisfaction of understanding and solving complex problems — with my desire to be able to build and create.

Computer science is underrated for the opportunity it gives to be creative, and you can iterate more quickly than almost any other discipline. I was particularly excited to study CS in an engineering environment at McCormick because I felt it would give me a chance to develop design thinking and work on interesting projects.

How did the McCormick curriculum help build a balanced, whole-brain ecosystem around your studies?

The core general engineering courses gave a solid foundation. The Design Thinking and Communication series was particularly useful because it provided experience working on longer-term projects than typical coursework and a view into interacting with real stakeholders.

I’ve also appreciated being able to branch out into neighboring fields, such as statistics or linguistics, and see how CS topics are approached from different perspectives. For example, I really enjoyed learning about natural language processing techniques both through machine learning courses and computational linguistics courses or studying probability through industrial engineering as well as algorithms courses.

What are some examples of collaborative or interdisciplinary experiences at Northwestern that were impactful to your education and research?

One standout experience was a special section of COMP_SCI 338: Practicum in Intelligent Information Systems that collaborated with the Knight Lab in the Medill School of Journalism . This was a project course in which each team was made up of a mix of CS and journalism students and each team built unique prototypes or tools at the intersection of AI and journalism. It was a great experience working on a more domain-specific project and benefitting from the perspectives of journalism majors.

What skills or knowledge did you learn in the undergraduate program that you think will stay with you for a lifetime?

I’m grateful for the research skills I’ve built. Obviously, courses are excellent for developing technical skills, but beyond that I feel that being able to work on many different teams has also massively improved my ability to communicate, present my ideas, and see projects to completion. I’ve gotten a lot of value from interacting with people from different backgrounds and areas of study.

What's next? What are your short- and long-term plans/goals in terms of graduate studies and/or your career path?

I’m preparing to apply to PhD programs focusing on machine learning research. My long-term hope is to contribute to the advancement of AI while ensuring systems are built and deployed safely through better interpretability and evaluation.

What advice do you have for current Northwestern CS students?

Research is much more accessible than most students think. I’ve learned so much through working in the NSAIL lab and being advised by Professor V.S. Subrahmanian in parallel to my classes — I wish I had tried to get involved earlier. In my experience, most professors are approachable and willing to support students.

In a similar vein, I found the most value in taking project classes and trying to dive beyond just the class material. The best learning experiences can happen when you engage with something very deeply, so take advantage of these opportunities.

McCormick News Article

• Engineering Home
• CS Department
• News Article

Recent Stories

Robot farmers? Machines are crawling through America's fields. And some have lasers.

CHUALAR, Calif. – Looking like the ungainly combination of a Transformer and Edward Scissorhands, the robot slowly trundles across the field of tiny plants. It uses three high-resolution cameras to peer down at the ground below. 

Lit by synchronized strobe lights, an onboard computer creates a digital image of each seedling as it glides by, comparing them with all the greenery it might reasonably find in a field of rich Salinas Valley farmland two hours south of San Francisco.  

In a fraction of a second, there’s a match – broccoli – and the computer hones in on the exact center of the plant, creating an on-the-fly chart of its placement.  

“It puts a dot on the stem and maps around it,” says Todd Rinkenberger of FarmWise, the robot’s maker. “Now it knows what’s plant. Everything else is a weed.” 

The robot’s circular set of metal blades smoothly move so they’re right in front of the plant, then snick open and shut, precisely digging into the soil one on each side of the broccoli seedling, destroying the weeds while leaving the sprout untouched, ready to grow to harvest size in another month or so. 

AGRICULTURE: Ancient farming practice makes a comeback as climate change puts pressure on crops

CLIMATE CHANGE: Weird weather hit cattle ranchers and citrus growers in 2022. Why it likely will get worse.

This all happens in a fraction of a second as the FarmWise Titan robot rolls down the field at less than 1 mile an hour. 

“It’s been quite a change,” said Luis Vargas, who started out on 20-person weeding crews in high school and now runs a fleet of four robot weeders for Tanimura & Antle, a grower and seller of fresh vegetables in California and Arizona.

“I remember being in the hand crews, it would be 10 hours days walking the fields. When you get into a super weedy field it’s slow, it’s hard. And it’s hot,” he said. “These machines, they don’t care if it’s hot or cold.” 

Farm robots could be good for human workers, farmers and the planet  

The scene in Chualar is being played out in a small but growing number of fields nationwide as robots using machine learning are deployed. Today, automated machines are mostly driving tractors up and down fields, carrying loads and doing thinning and weeding. Other systems deploy precise doses of fertilizer or herbicides. But harvesting, especially delicate fruits and veggies, is further off in the future. 

Together, machines are set to help solve a host of problems. The biggest is reducing the need for backbreaking agricultural jobs. Workers will still be needed, but more will be running the robots, fewer doing tedious, physical labor. It’s already resulting in a host of new jobs for people who can build, run and repair the systems. Community colleges and universities are busy creating programs to teach these skills to a new generation of agricultural workers. 

Experts say agriculture is a rare application of cutting-edge technology that workers, tech companies, the government, and big business are all to varying degrees optimistic about. 

READ MORE: Latest climate change news from USA TODAY

How does climate change affect you?: Subscribe to the weekly Climate Point newsletter

Another perk of robots, nonintuitive for people outside agriculture, is that they’re smaller and lighter than traditional large tractors. This means farmers can get working in fields early, when the ground is still too wet to bear the weight of large tractors and cultivators, giving farmers a longer growing season without worries about compacting and harming the soil. 

“This is important especially with climate change because we’re expecting wetter springs and drier summers,” said Steven Mirsky, a research ecologist with the United States Department of Agriculture. 

‘It’s a hard job’ 

Labor is a huge driver of the change, said John D’Arrigo, president of D’Arrigo California. His family has been growing lettuce, broccoli, cauliflower and broccoli rabe in California for three generations, and he sees his workforce aging out. 

“We’re cutting 1 million heads of lettuce a day and it’s a hard job,” he said. “The people walking in the fields, bending over cutting lettuce? Those people are disappearing, they’re retiring,” he said.  

Where there's caution, it's from unions that want to make sure their workers enjoy the benefits of automation and help decide how it's rolled out. T he United Farm Workers of America isn’t seeing robots displacing humans in the fields, said communications director Antonio De Loera-Brust. 

Its biggest concern is that the technology be deployed to make agricultural jobs better, not make them go away. 

“Is this going to be deployed to make farm work safer and take less of a toll on people’s bodies?” he said. “Or is this just going to be another tool to maximize profits on the back of farmworkers? We want workers to have a say in how robots get implemented.” 

D’Arrigo says agriculture has to make its jobs better.  

“I’m losing people to construction,” he said. “If we’re going to survive as an industry, we’re going to have to make jobs that are more lucrative and interesting.” 

More: In San Francisco, the cars are driverless, the humans are baffled and future is uncertain

That’s certainly been the case for Vargas, 27. His mother has worked for more than 14 years in the packing sheds at Tanimura and Antle.

Vargas went to college with the goal of working in criminal justice, but the new tech possibilities intrigued him. He started working on the first demonstration Smart Cultivator robot systems from Stout Industrial Technology in Salinas about four years ago.  

Today, the robot crews he manages can weed about an acre an hour. 

“For a hand crew it would take about 20 people,” he said.  

Farms are already more high-tech than you think 

Agricultural robots and automated systems are mostly invisible to people driving by a field, said Emily Duncan, an agricultural technology and innovation researcher at the University of Guelph in Ontario, Canada. 

That can be as simple as a tractor or combine that drives itself along a field of corn or wheat or soybeans. Called auto steer, these systems use GPS and only require that the driver turns at the end of the row. 

“When you’re out harvesting 12, 13, 14 hours a day, driving for so long is really tiring. Using this, you’re mostly monitoring,” said Duncan. 

As of this year, such systems are being used in more than 50% of row crops such as corn, soybeans, cotton and winter wheat , according to USDA.

The next level up will be machines that use high-resolution cameras to see each plant and give it a precisely measured squirt of fertilizer, depending on how well the plant is doing. If it’s puny, it might get more, if it’s nice and robust, then less. 

In some cases, ag robots can do things that simply couldn’t be done before. One example is small robots that can navigate and weed under the canopy of a cornfield after the plants have grown high. Any weeds, even hidden ones, take nutrients and moisture from the soil that could go to crops.

“Now we just accept those weeds because we can’t get to them,” said Shadi Atallah a professor of agricultural economics at the University of Illinois Urbana-Champaign, where the robots are being developed.  

Robots could also make organic foods cheaper. Today organic crops rely on more cultivation and hand work than conventional crops because herbicides can’t be used, which makes them more expensive to grow. Robots offer an alternative. 

“Organic can mean having workers bending over the whole day just so somebody who can afford it can buy an organic vegetable,” said Atallah. 

In addition to mechanical robot weeders, there's the laser weeder from Carbon Robots, which uses 30 lasers to zap weeds or thin seedlings, with no hand labor or chemicals required.

One other place robots can make a big difference is in cover crops , the growing practice of planting things like winter rye, hairy vetch and crimson clover in newly-harvested fields to lock in moisture and strengthen the soil, then cutting them down to enrich the soil before planting again in the spring.  

Today such crops have to be sown after a field is harvested, or by airplane, dropping seeds from the sky. But robots can scoot under the canopy of corn, soybeans and cotton and plant cover crop seed before the main crop is harvested. 

“This will expand the ability to do cover cropping and take less time. It’s not reducing labor intensiveness, it’s using artificial intelligence technology to help with the sustainable transition of agriculture,” said Atallah. 

'Robot hands are getting better but they’re not there yet'

A stumbling block is finding tech people to apply their knowledge to agriculture. That’s one reason the Western Growers Association created its Center for Innovation and Technology in Salinas. 

But while it’s only an hour south of Silicon Valley, “there’s a real disconnect between people who work in tech and people who work in ag,” said Duncan.

The problems farmers face are difficult to solve and don’t offer the kind of global scale tech firms like. Each crop type can require a new solution. 

“I spoke to an audience of venture capitalists a few years ago,” said Neill Callis with Turlock Fruit Co., a fourth-generation melon farm in California’s Central Valley.

“I was describing the melon-picking problem and they were all ears. Then I said it’s really a $30 to $60 million problem space and you could just see the lights go out. There just wasn’t enough upside for them to raise the money and innovate to solve our specific problem.”

Today, interest is ramping up, as shown by the host of smaller robot startups launching. "Ten years ago, none of these people were here," said D'Arrigo. "Now there's lots of them around but we need lots more to get into it."

Harvesting will be the last problem solved, especially when it comes to fruits and vegetables, said Dennis Donohue, director of the Center for Innovation and Technology.  

“It turns out killing weeds is easier than delicately plucking strawberries," he said. "Robot hands are getting better but they’re not there yet."

It’s also got to become a whole lot cheaper. “Picking an apple for $20 is a non-starter. It’s got to cost 2 cents,” said Callis.  

A revolution in small farms?

In the end, robots could revolutionize farming, making smaller farms more economical and the entire industry more sustainable, changing an agricultural world in which the model has long been “get big or get out.” 

“Once you work with a scale-neutral technology like robots, you’re no longer saying you can only survive if you have the biggest combine. The question becomes, ‘Are you a one-robot farm or a 30-robot farm?’” said Steven Mirsky, a research ecologist at the Department of Agriculture who's building the public databases of images ag companies can use to jumpstart their systems.  

Startups like Farm-ng in Watsonville, California, are now building small, easy-to-configure robot platforms that farmers can add onto for whatever they need, which USDA is experimenting with, he said. Moving away from huge, massive, and massively expensive, equipment to light robots that will be modular and easier to fix can also enhance the kind of technical ingenuity that has long been the hallmark of the American farmer.

One thing Mirsky is sure of – machines will never entirely supplant farmers.  

“The farmer is the ultimate multifactor analyses machine,” he said. “You can’t replace them, you can only add capacity for them to do what they need to do,” he said.  

Our lobby is open 9:00-5:00. We also offer virtual appointments.

Our lobby will be closed 2:30-5:00pm June 12th and all day June 18th & 19th.

• Undergraduate Students
• Graduate Students
• Recent Graduates & Alumni
• Staff & Faculty
• Managers of On-Campus Student Employees
• Career Fairs
• Online Resume Review
• Drop In Coaching
• Career Coaching Appointments
• Workshops and Events
• Career Courses
• Connect with Employers
• Connect with Alumni & Mentors
• Free Subscriptions for Huskies
• Private Space for Virtual Interviews
• Husky Career Closet
• Professional Headshots
• Find Purpose
• Build Skills
• Get Experience (internships)
• Build Relationships (networking)
• Tell Your Story (profiles, resumes, cover letters, interviews)
• Find Success (jobs, service programs, grad school)
• Arts / Media / Marketing
• Consulting / Business
• Non-profit / Social Justice / Education
• Law / Government / Policy
• Physical & Life Sciences
• Sustainability / Conservation / Energy
• Tech / Data / Gaming
• First Generation Students
• International Students
• LGBTQ+ Students
• Students of Color
• Transfer Students
• Undocumented/DACA Students
• Student Veterans
• Students with Disabilities
• Featured Jobs & Internships
• Handshake Access Details
• Internship Advice
• On-Campus Employment
• Job Search Tips
• For Employers
• Peace Corps
• Diplomat in Residence
• Baldasty Internship Project
• Get Involved

Machine Learning Applied Scientist Intern – PhD (Boulder, CO – Summer 2024)

• Share This: Share Machine Learning Applied Scientist Intern – PhD (Boulder, CO – Summer 2024) on Facebook Share Machine Learning Applied Scientist Intern – PhD (Boulder, CO – Summer 2024) on LinkedIn Share Machine Learning Applied Scientist Intern – PhD (Boulder, CO – Summer 2024) on X

Splunk is here to build a safer and more resilient digital world. The world’s leading enterprises use our unified security and observability platform to keep their digital systems secure and reliable. While customers love our technology, it’s our people that make Splunk stand out as an amazing career destination and why we’ve won so many awards as a best place to work. If you become a Splunker, we want your whole, authentic self, what we call your “million data points”. So bring your work experience, problem-solving skills and talent, of course, but also bring your joy, your passion and all the things that make you, you.

Role Summary

Splunk is looking for PhD students to join our team for Summer 2024! As a Machine Learning Applied Scientist intern, you will work on a real project (or a few) and have an opportunity to enjoy our dynamic, startup-like environment.

You will experience Splunking and what defines our culture while honing the skills which separate our development teams from others. Working to support internal and external customer needs, you will collaborate with multi-functional teams, receive mentorship, and gain insight into our values-driven process. Our goal is both to support your growth and development while empowering you for a successful start to your career.

What you’ll get to do

• Achieve data science and software engineering goals set by you and your mentor
• Learn about Splunk, both the product and the company
• Work and socialize with other interns and full-time Splunkers

Must-have Qualifications

• Actively pursuing a PhD in Computer Science, Software Engineering, Computer Engineering, Electrical Engineering, Mathematics or a related technical field, and a strong record of academic achievement.
• At least one semester/quarter remaining to complete after the internship
• Available to work 40 hours a week for 12 weeks

Nice-to-have Qualifications

We’ve taken special care to separate the must-have qualifications from the nice-to-haves. “Nice-to-have” means just that: Nice. To. Have. So, don’t worry if you can’t check off every box. We’re not hiring a list of bullet points–we’re interested in the whole you.

• Coursework and research experience in machine learning, either time series analysis (univariate and multivariate) with a focus on anomaly detection OR in Generative AI technology and Large Language Models (LLM)
• Experience with ML frameworks (e.g., TensorFlow, PyTorch) and Python.
• Ability to work well with others in a fast-paced environment
• Experience working in an agile environment
• Strong communication skills, verbal and written
• Enthusiasm for solving interesting problems
• Experience programming in a large software project – at school, professionally, or in an open source context

Our Splunktern Program allows incoming interns the flexibility to choose from three start dates, currently anticipated to be:

• Monday, May 20, 2024
• Monday, June 3, 2024
• Monday, June 17, 2024

Candidates should consider their availability to start on one of these three dates prior to submitting an application. Please note: the dates above are subject to change at Splunk’s sole discretion.

Splunk is an Equal Opportunity Employer

At Splunk, we believe creating a culture of belonging isn’t just the right thing to do; it’s also the smart thing. We prioritize diversity, equity, inclusion, and belonging to ensure our employees are supported to bring their best, most authentic selves to work where they can thrive. Qualified applicants receive consideration for employment without regard to race, religion, color, national origin, ancestry, sex, gender, gender identity, gender expression, sexual orientation, marital status, age, physical or mental disability or medical condition, genetic information, veteran status, or any other consideration made unlawful by federal, state, or local laws. We consider qualified applicants with criminal histories, consistent with legal requirements.

Connect with us:

Contact us: 9a-5p, M-F | 134 Mary Gates Hall | Seattle, WA 98195 | (206) 543-0535 tel | [email protected]

The Division of Student Life acknowledges the Coast Salish people of this land, the land which touches the shared waters of all tribes and bands within the Suquamish, Tulalip, and Muckleshoot Nations. Student Life is committed to developing and maintaining an inclusive climate that honors the diverse array of students, faculty, and staff. We strive to provide pathways for success and to purposefully confront and dismantle existing physical, social, and psychological barriers for minoritized students and communities. We engage in this work while learning and demonstrating cultural humility.

Our website uses tracking cookies. By clicking "accept" you give your permission to this website to use tracking cookies.

Click here for our privacy and cookie policy Accept Deny

• Search Working at TU/e
• Academic Perspectives
• Irène Curie Fellowship
• Professional Development
• Scientific Staff Vacancies
• Support Staff Vacancies
• Compensation and benefits
• Application process
• Support for internationals

Working at TU/e

Phd position in causal machine learning, job description.

The Uncertainty in Artificial Intelligence (UAI) group is a quickly growing group embedded in the Data and AI (DAI) cluster at the Eindhoven University of Technology (https://dai.win.tue.nl). In the DAI cluster, we aim at developing foundations of AI for the present and the future. This includes the design of new AI methods, development of AI algorithms and tools with a view at expanding the reach of AI and its generalization abilities. In particular, we study foundational issues of robustness, safety, trust, reliability, tractability, scalability, interpretability and explainability of AI.

The UAI group is looking for a highly motivated and skilled PhD candidate to work in the area of Causality. The concrete research direction will be determined together with the successful candidate. The research topics include, but are not restricted to:

• Causality: Theory and Application.
• Causal Probabilistic Circuits.
• Causal Representation Learning.
• Causal Explanations.
• Causality and Large Language Models.
• Counterfactual learning.

Job requirements

• Master’s degree in Computer Science, Mathematics, or a related field.
• Excellent analytical skills.
• Excellent coding skills (e.g. Python, PyTorch, Tensorflow).
• Excellent academic writing and presentation skills.
• Proficiency in English (written and spoken).
• Desire to conduct excellent research and publish in high quality conferences and journals.
• Independent thinker and self-responsibility.
• Ability and desire to collaborate and work in teams.
• Ability and desire to support teaching and to co-supervise bachelor and master students.

Conditions of employment

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you:

• Full-time employment for four years, with an intermediate evaluation (go/no-go) after nine months. You will spend 10% of your employment on teaching tasks.
• Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale P (min. €2,770 max. €3,539).
• A year-end bonus of 8.3% and annual vacation pay of 8%.
• High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process .
• An excellent technical infrastructure, on-campus children's day care and sports facilities.
• An allowance for commuting, working from home and internet costs.
• A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates.

Information and application

Eindhoven University of Technology is an internationally top-ranking university in the Netherlands that combines scientific curiosity with a hands-on attitude. Our spirit of collaboration translates into an open culture and a top-five position in collaborating with advanced industries. Fundamental knowledge enables us to design solutions for the highly complex problems of today and tomorrow.  Curious to hear more about what it’s like as a PhD candidate at TU/e? Please view the video.

Information

Do you recognize yourself in this profile and would you like to know more? Please contact the hiring manager assistant professor dr. Devendra Singh Dhami, email [email protected].

Visit our website for more information about the application process or the conditions of employment. You can also contact HR Services, email [email protected].

Are you inspired and would like to know more about working at TU/e? Please visit our career page .

Application

We invite you to submit a complete application by using the apply button. The application should include a:

• A research statement, including research experience and interests, and a short outline of the preferred future research direction (max. 1 page).
• A CV, including education history, relevant courses and theses, research experience (if available), a list of publications (if available), and teaching experience (if available).
• Transcript of records for Bachelor’s and Master’s degrees.
• Electronic copy of (or a link to) Master thesis.
• Electronic copy of publications (if available; if more than 3, please submit top 3). If no publications are available, please submit some substitute, e.g. presentations slides of a given presentation.
• Contact details of or recommendation letters from 2 referees.

We look forward to receiving your application and will screen it as soon as possible.  The position may be filled early if a suitable candidate is found, so do not wait until near the deadline to apply. Applications are only accepted via the dedicated web system (do not send applications via email). 

PhD Defence Hamed Darbandi | Non-Invasive Fitness Assessment In Horses - Integrating Wearables and Machine Learning

Non-Invasive Fitness Assessment In Horses - Integrating Wearables and Machine Learning

Hamed Darbandi is a PhD student in the Department of Pervasive Systems. (Co)Promotors are prof.dr. P.J.M. Havinga† and dr.ir. B.J. van der Zwaag from the Faculty of Electrical Engineering, Mathematics and Computer Science.

Conventionally, veterinarians and researchers have devised methods to interpret equine well-being, including verbal encouragement, facial expressions, and blood sample analysis. The former two methods are subjective, relying on experienced individuals and laboratory environments for interpretation. The latter, while informative, is invasive, inducing stress and discomfort in horses during sample collection. It is also cumbersome, as it necessitates multiple interruptions to training sessions for sample collection. Furthermore, inaccurate or unreliable fitness parameter values can compromise the foundation of an effective training plan, potentially resulting in adverse outcomes such as overtraining and injury. Therefore, it is crucial to implement a method akin to those used in human sports, capable of providing feedback, and to choose a portable measuring device that can accurately and reliably assess fitness metrics. This device should be designed for field use, enabling assessments outside of a laboratory setting.

This PhD thesis aims to revolutionize the training of sport horses by exploring the use of inertial sensors as wearable technology and the incorporation of state-of-the-art machine learning to enhance equine performance while preventing injuries. The study unfolds in nine chapters within two interconnected parts, with each contributing a crucial piece to the overarching goal of enhancing equine fitness and well-being.

Each chapter begins with a review of the existing literature, identifying gaps and challenges in equine fitness and performance. Based on the reviews, inertial sensors were selected as the most suitable technology for their ability to capture a wide range of real-time motion data. The chapters then focuses on using the measurement system by placing it on the horse's body, including the head, neck, shoulders, back, and legs. The measurement phase involves various training and competition scenarios, with data collected and analyzed to evaluate the system's effectiveness. The results reveal the system's capacity to accurately capture and analyze a broad spectrum of motion data, providing valuable insights to trainers and riders for fitness improvement and injury prevention.

This thesis represents a significant stride in equine research, leveraging wearable sensor technology and machine learning to enhance our understanding of equine fitness, performance, and well-being. The knowledge gained from these chapters informs not only the scientific community but also the broader equestrian world, offering practical tools for improving the welfare of sport horses. By providing feedback through the evaluation of fitness during training sessions, this technology has the potential to enhance performance and contribute to the sustainability of the equestrian industry.

More events