We love collaborating with smart researchers on new ideas, and this one is no exception! Oamk approached us to ask that if Iris.ai could read research papers and patents and reduce the time to navigate that landscape, surely she could do the same with funding applications? And sure thing – we have now equipped a special version of Iris.ai with all EU-funded projects since 2014, with the aim to improve the efficiency and productivity of RDI project preparation, especially in tightly competitive European project funding. Giving researchers the ability to map out state-of-the-art funded research, new projects can be rapidly targeted to novel research challenges.
Oamk will pilot the new tools in their upcoming H2020 project preparation in the fields of printed intelligence, drones and development of regional innovation systems.
We are looking forward to them piloting the new application of Iris.ai and seeing the positive results on their application processes.
If you are curious about the details of the project and its outcomes, you are welcome to contact Karita Kasurinen on email@example.com.
Map subscriptions, BibTex exports, patents, dark mode and algorithm improvements – and some changes to free and premium versions.
It’s that time yet again – last night we pushed out some new and exciting changes to the academic tools! There’s a long feature list below, some of which (including map subscription and BibTex export) are long time favourite feature requests. We hope you enjoy them!
The main change with this launch is in the logic of free and premium accounts. We’ve made some choices on this front driven by a few reasons: a) We’ve now properly established ourselves with an offering toward university libraries, and found a collaboration model that universities can afford and that we can live with. That means more and more users are coming in through University licenses and have access to the full premium tools, which makes us very happy! b) We see that the decidedly best experience one can have with the tools is to have access to it all. c) At the same time, we wanted to give free users the ability to get a feeling for all of the tools, not just the Explore tool.
In short, as a free user we’re limiting some more of the features in the Explore tool, but opening up the ability to try out the Focus tool as well – and we’re starting to Beta test an individual payment model, if you want easy access to all of the tools and features! (Send an email to firstname.lastname@example.org for more information)
With that said, let’s dig into the details. The ability to use the tools without being registered even with a free account is heavily reduced. You can engage with shared Exploration maps and Focus studies, but you can not create them nor edit them.
For free user accounts, we chosen to limit some features including the ability to input your own problem statement and search in patents. You will see the Focus tool now being available in your account, and be able to import single Explore maps into a Focus study.
If you urgently miss some of the features we have had to remove from the Free tools, or want full access to the features of your new Focus tool, there are two ways to go about it: 1) Talk to your librarian about getting the entire university/department access to our tools or 2) Contact email@example.com to inquire about individual premium access.
Dark mode: Let’s face it – we’re all different, and we figured we’d add a neat little feature for those of you who prefer the darker side of life. Toggle on dark mode on top of the left hand menu for a new Iris.ai experience.
Subscribe to maps: Have you built the perfect map that contains state of the art of what you need, and would love for us to let you know whenever new relevant content is found? It’s one of our most requested features and it’s here! Subscribe to your favourite maps and receive notifications whenever the content change with new relevant papers.
Easier content selection: Do you want to search by patents, papers, or both? This is now a lot easier to choose – either as you input your research question or starting paper, or in the map itself, which will regenerate the map.
Export your map results: Another highly cited request – this feature allows you to export the list of papers in your result map as a .csv file, or in BibTex format for uploading to your favourite reference manager system.
Bye-bye, TED talks! When we started building Iris.ai, we found a fun way to build something that made sense and demonstrated our intention and vision – but that didn’t require the full capability of reading millions of research papers. The concept we launched early 2016 was “see the science around a TED talk” and allowed you to pop a TED link into the tool, Iris.ai would machine read the script and show you a science map. Years later, while we will care deeply for our little hack, we figured it was time to retire support for this practically unused feature. So goodbye, little TED-Science-tool, it was a pleasure having you with us!
Algorithmic and capability improvements. We keep on improving the core engine, and the new improvements this time around are connected to an improved keyword extractor module (using tf-idf to propose candidates for key words, and then topic modeling to evaluate the relevance of those candidates) and the first part of better word disambiguation (w2v, currently disambiguating on part-of-speech, which helps finding better synonyms for e.g. words that are both noun and verb or other variations), and a new algorithm for hierarchy building to create smarter concept maps for the Explore tools (uses not only topic information and similarity, but also generality and concept dependencies to form the final output), freshly tuned hyperparameters that give better results overall – and some general system performance upgrades and updates.
The Nordic AI Alliance is made up by leading Nordic companies, all working with AI, and create stronger collaboration structures between the Nordic countries. The members of the Nordic AI Alliance pledge to help facilitate this acceleration, by helping other companies and organizations in the Nordic countries come in contact with the best expertise to help them throughout their AI journey.
“Openness and transparency are going to be vital to the safe and sane application of AI to real and important problems. We cannot sit on our individual and fairly arbitrary patches of land and pretend the rest of the world does not exist. What we have in the Nordic region is a sense of trust and fairness which are core drivers for openness and transparency – these values seep through our company culture and we’re looking forward to sharing and learning from each other.”
– Anita Schjøll Brede, CEO & co-founder, Iris.ai
Artificial Intelligence (AI) is already being used to solve some of the world’s biggest challenges and is being put at the core of change by organizations and countries around the world at an increasing pace.
The Nordic countries have strong regional values ensuring that everyone in society benefits from advancement in technology and research.
To remain competitive the Nordic Countries need to increase the pace at which they adopt AI technology at the core of business and infrastructure.
The challenges of AI
AI offers a cognitive increase in any organization’s capability to make predictions, support systems, automation and computer vision systems related to their products and services. To adopt AI as a change driver and become ‘AI First’ is challenging. The members of the Nordic AI Alliance are leaders in each of the seven areas of this journey:
01/ Basic knowledge & understanding of AI 02/ Becoming a data driven organization 03/ Mastery of data 04/ AI Expertise 05/ AI tooling suited for business 06/ Organizational evolution 07/ Designing and building AI products & services
Many of the Nordic Alliance Members have an international presence with several offices worldwide. The location listed below is the HQ.
We live in a world where an estimated 6,800 scientific papers are published every day (source). Yet, navigating such a huge influx of data and information is nearly impossible for any one human being or even a team of human beings. No wonder there is rampant misinformation, conflicting claims, and confusion about how best to tackle such an immense and multi-faceted challenge as climate change.
Enter, Artificial Intelligence. Now that we have the technological ability to generate and store so much new knowledge, companies like Iris.ai are now focused on training artificial intelligence to tackle all of that information and make it digestible for researchers, especially when time is of the essence as it is with the climate crisis.
The first challenge at hand for any researcher is to determine what information exists on a given topic. For example, this list of the most cited papers on climate change. These 10 papers are a start, sorted to the top of the pile based on the number of other researchers who have declared them relevant through their use of the data in their own papers. However, there are hundreds if not thousands of papers related to these 10 that could present new, valuable information, that is only ever seen by a small handful of people (source).
Using Iris.ai’s exploration tool, we built maps of existing open-access knowledge based on 5 of the 10 most cited papers, revealing 1,271 other papers directly related to the concepts within. 1,271 papers that may help us further flesh out existing findings and come up with new solutions faster.
What to do with 1,271 papers, though? Now that the knowledge is found, we’re still humans with an immense processing challenge ahead of us, i.e. reading all of those papers.
The same algorithms that helped to discover those papers can help to narrow them down as well. With tools like the Iris.ai focus tool, you can step behind the curtain, as it were, to drive the AI herself and systematically narrow down that overwhelming list, into the handful of papers that are most highly related to your specific field of research.
What you end up with is a list of highly curated scientific articles, clear from the limitations and biases of keywords or impact factor, and available to consume in less than 20% of the time it would normally take to compile such a list through traditional search tools.
Through this process, tech companies and researchers across the globe can more easily understand the state of the climate and move toward clear plans for action even faster than before, diving into the World Economic Forums other 11 suggestions fully informed and ready to make change.
The world needs science. Complex challenges ranging from climate change to preventive medicine require us to put our best minds together to solve them. And we do live in a world where more scientific knowledge is available to us than ever before — but the irony is that our politicians doubt its legitimacy, our researchers are pressed for time and resources do not have capacity to communicate across even the closest alleyways of a university, publishing houses generate profit by keeping vital results hidden behind heavy walls, and go after those who breach them with deadly force. In addition, the big software players are opaque and seemingly impossible to hold accountable for their data, their algorithms and the implications of these. In spite of Tim Berners-Lee creating the internet to share scientific knowledge, it seems we have only come marginally further today than we had back then.
Two years ago at Iris.ai we sat out on quite the ambitious journey: to build what we call an “AI Scientist”, a system that can augment our human intelligence by connecting the dots of all of the world’s research. The months since have been filled with hard work, progress, setbacks, a lot of rejections — but also so much love, support, understanding and encouragement from our wonderful community.
In these two years we’ve built a system that reduces a human’s time to map out existing scientific knowledge with up to 90% , while increasing serendipity and interdisciplinary discovery. This is the first important step towards what we call the Knowledge Validation Engine, a core feature of the AI Scientist. We have a dedicated team that has built this, we have a number of budding university collaborations and we have a group of lovely investors who believe in us and we’ve published several open access research papers. Most important, this past year we’ve seen an amazing community of AI trainers grow up around us — more than 8,000 individuals who volunteer their time to help Iris.ai learn. We’ve seen a desire to be part of our journey, a wish to help us achieve our mission, a community coming together to tell us that what we do is important. We have done our best to honor their help, but we have not done enough.
Transparency, openness and fighting bias have been our core values from day one, but we find ourselves not living up to our own standards. We find ourselves torn between servicing big corporate clients and satisfying a European venture capital community single-mindedly focused on revenue (with some very honest impact focused exceptions) on one hand — while also trying to bring what we build out to as many people as possible.
For us to truly make impact in the world, it is not enough to build some great tools, we need to disrupt and uproot an entire industry. We can not do that on our own — it’s a grassroots challenge. We need your help.
Scientific knowledge is arguably the ultimate decentralized application. It is not controlled by a central agent, is individual node-independent, is exposed to public scrutiny and constant challenge and is preciously valuable for a large and fast growing cohort of current and future users.
The technology development of this decade is thrilling, and today we are taking advantage of a new opportunity. Utilizing the decentralized nature of the blockchain, we have decided to give power to our community by tokenizing our functionalities— allowing anyone who contributes to the tool to generate tokens by doing so — tokens they can later use directly to access our core services.
An AI Trainer who annotates research papers, a coder who commits to our increasingly open source code, a user who reports a bug or a researcher who uses the Iris.ai Knowledge Validation Engine to publish their research Open Access — they will all be rewarded with tokens for contributing. The tokens can be used to access any of the Iris.ai tools. All token holders will have a voice, have transparent insight into our core technology and will be asked to hold us accountable to openness and de-biasing our algorithms and data. And as both corporates purchase access to the Iris.ai tools and the the algorithms of Iris.ai improve over time, the value of the tokens held by our community will increase.
We’re excited, thrilled and a little scared — as per usual, we’re traversing unchartered territory. And we can not do this alone. Please join us in making science transparent, open and accessible.
Our white paper with the details will be made available early 2018. Until then we would love your ideas, thoughts and feedback — on firstname.lastname@example.org or our Telegram channel.
Iris.ai provides multidimensional research for exploring possibilities and limitation in applying Augmented reality to surgical settings
Last week we hosted a Scithon in collaboration with Stryker and the Freiburg University Medical Center. For this Scithon, three teams were trying to find a solution for this research question: What research and development work is necessary to build a “ready to use” adaptive augmented reality (AR) system for surgeons to teach them how to perform a surgical procedure? The judges were looking for the teams to find solutions involving four different dimensions of the question; identifying the capabilities of the technology, outlining the training process for doctors, describing the human interaction and UX and how it would be integrated into the surgical flow. Over the course of the day, we had several conversations with participating doctors and members of the Stryker team which gave us valuable insight and solid background information for the research problem we were trying to solve.
The Scithon’s winning team cited just 13 papers using Iris.ai which allowed them to successfully cover all four of the required angles. The team concluded that the prospect of AR in surgical environments is absolutely feasible however the current technology needs further testing to prove reliability and other improvements to meet surgical requirements. They were able to outline specific uses of the technology and identified that ‘the more rigid and basic the surgical system the easier it is to implement augmented reality applications to improve results.’
The team placing second used traditional research methods to reach their conclusion and while they found more papers, 46 in total, those papers had a much more narrow focus, with most of them targeting a single topic area. The reason being, traditional methods rely on the existing knowledge of the user, where users typically search for more of what they know instead of discovering new, related topics that were previously unknown to them. Their conclusion ascertained that presently there is no technology that encompasses all of the features needed to create an AR system to satisfy all of the requirements named in the problem statement. However, research data and solutions on the key aspects of technical limitations are available and provide the foundation for the development of the envisioned system.
Similar to the winning team, the team that placed third was also using Iris.ai and was able to reach their conclusion using a few number of papers citing 15. While the judges were conflicted on the depth on which they covered the various aspects of the research question, they were able to cover 3 out of 4 of them. Their solution asserted that it is possible to build an AR system comprising of existing surgery navigation platforms, real-time intraoperative imaging and 3D visualization display devices. However, these technologies are not without shortcomings like the need to reconfigure display devices that are too bulky, have limited capabilities and autonomy limitations and improve the tracking of surgical instruments and automatic relevant medical information extraction.
The results of the Scithon spoke to the benefit of Iris.ai’s serendipitous search enabling a multi-faceted approach to research. Whereas traditional search limits the output to singular aspects of the problem, that doesn’t connect all of the possible angles. Current keyword search engines return results that can be biased based on the user’s search history and experience. Iris.ai produces unbiased, objective results creating a multidimensional approach for research discovery. Most research problems require several topic areas to be considered before a solution can be found and Iris.ai enables teams to find the research to cover each and every one of them.
Gaining context for the research problem we’re trying to help solve
Last week, we hosted a Scithon in collaboration with Stryker, Augmented Vision and Freiburg University Medical Center. We put a group of medical engineers, IT experts, neurosurgeons and urologists in a room to discuss and research methods for advancing Augmented Reality/Virtual Reality in surgical settings. What made this particular group of Scithon Participants unique was the high level of expertise related to the research topic subject matter. Even before beginning to research the feasibility of AR/VR surgical innovations, almost all of the doctors already had a good baseline of specific features or use cases that would be most beneficial to them. And the views between neurosurgeons and urologists regarding the usability and implementation of innovative technology in the Operating Room varied greatly. It seemed clear that no matter the outcome of the day’s research, the feasibility of using AR/VR in the OR wasn’t the biggest obstacle to overcome. So, before we outline the results of the research, we want to the highlight a few of the learnings from the discussions that took place over the course of the Scithon. These learnings provided valuable context for the day’s research and gave us better insight into the pain points behind the research question.
Coming into the Scithon, it was interesting to see what types of technologies the doctors had begun to familiarize themselves with and which ones they preferred. One of the urologists touted his ‘bootstrapped’ method of incorporating Google’s Cardboard into his work while other teams of neurosurgeons already begun investigating how best to use Microsoft’s HoloLens. Other doctors expressed frustration at the speed of their colleagues’ ability to embrace and adapt to new technologies. And still, others, questioned the practicality of implementing a new technology that will need to be replaced in 3 years or even worse, could be obsolete in that same period of time. Even with the ability to use groundbreaking technology, there are other issues creating barriers for implementation. Hospital budgets, time spent training doctors, access to up to date research and data, IT maintenance, etc are all factors in delayed or even non-use of state of the art technology.
How residents and doctors time is spent was a recurring theme mentioned throughout the day. The finite preciousness of doctor’s time is a never ending issue. Several participants stated it was difficult being able to attend today’s Scithon, let alone focus on their own research. The sacrifice of their time did pay off, as all they agreed that the Scithon was a valuable use of their time. It allowed for a ‘meeting of the minds’ type atmosphere facilitating extensive discussions among a range of medical specialties. And many were interested in the long-term possibilities of using Iris.AI’s platform to expedite their institution’s research. Ability to save time was a vital feature that all participants were interested in, regardless of specific technology.
We gained numerous insights from the medical technology provider and manufacturer group of participants as well. We could relate to them as we were both in the position of watching, in real time, others using our products and platform. The participants from Stryker shared a few industry insights like Microsoft’s shift from AR back to their primary Cloud based product offerings and how that might affect their future involvement with the AR field. They also discussed a slight gap between product features and product implementation in the medical field, as some doctors had mentioned their products were too complex for what they needed. Simply put, the current technological solutions were overbuilt. The feedback is at the forefront of their minds as they continue to create products for the medical community.
They say if you build it, they will come it. Well, now the question is, can they build it? Does AR/VR have a place in surgical settings and if so, how can it best be implemented?
Can Virtual and Augmented reality improve the medical training process?
Virtual Reality & Augmented Reality are changing the world as we know it, every day we are discovering new uses for these innovative technologies. The medical field is one that is especially excited to see the applications of VR and AR evolve, as the implementation of these frontier technologies could improve medical education considerably. The nature of practical medical training has changed minimally over the last decades. However, the feasible application of VR & AR for medical education purposes could modernize the training process for medical students, requiring less training performed on patients. Understandably when education for treatment methods improves it allows for medical staff to address the needs of patients in an increasingly comprehensive manner. And it It is these notions that form the basis for our upcoming Scithon.
Next week researchers from the Division of Urotechnology, University Medical Center Freiburg, in cooperation with the Department of Augmented Vision, German Center for Artificial Intelligence, and the Stryker Stryker Leibinger GmbH & Co. KG, will gather to compete to find the best approach to implementing these technologies. VR & AR are ever growing fields, with new information published daily, so the teams will us Iris.AI to find the most relevant papers to this query. Because Iris.AI shortens the amount of time needed for research discovery, it enables teams to move to the next stage in research & development more quickly. This correlates to identifying new solutions and avenues for treatment of patients more quickly which can ultimately save lives.
We are excited to put Iris to work on such a considerable task with far reaching results and benefits. We look forward to sharing these promising results with you next week.
Hitting a roadblock in your research? Struggling with the drudgery part of the R&D process?
Here at Iris.AI we thrive on addressing multifaceted issues head on and love being able to use our AI to help others elevate their innovation process. In fact, we love it so much that we are dedicating our summer to do just that by running a tour of Scithons in London, Stockholm and San Francisco in collaboration with Founders Factory.
Each Scithon (think of Hackathons for research!) is a day-long research sprint where teams of driven researchers use Iris.AI to summarize the most relevant research on an R&D challenge in one day. Teams, invited to the event by Iris.AI, compete to win a cash prize by pioneering a tangible solution to the question at hand.
At the end of the day you will receive the winning team’s solution which will contain:
– A full overview of all identified cross-disciplinary research on the challenge
– Their conclusion on how to go about solving the problem
– The key papers outlining this solution.
– You will also have contact details of the team’s participants in order to continue the dialogue with them.
We are now looking for innovation-driven organizations to join us for the sprint in one of the three cities. Simply send us your research question. We’ll take care of everything else including the sourcing of multidisciplinary and driven researchers.
Iris.ai gives students, researchers, and engineers alike, the tools to realize and actualize their (spatial) dreams. And in this case, dreams of making aerospace history.
Two months after SpaceX’s Dragon launch mission, Iris.AI hosted a science hackathon or Scithon as we like to call it, in partnership with the leading composite materials research institute Swerea SICOMP. At the Scithon, we challenged researchers to find solutions to this question, “Can you create a reusable rocket using composite materials?” A concept that SpaceX has been pursuing for 15 years while the research community has been exploring such possibilities for much longer than that. Yesterday’s historic launch was the first step in achieving that milestone by attempting to mimic the reusable nature, lifespan and quick turnaround of planes used for air travel.
Before launch, SpaceX engineers pointed out that there are a thousand ways to fail, but only one way to succeed and identified the areas of possible failure; manufacturing error and material fatigue and wear out. The areas identified by SpaceX were a generalization of the known obstacles at the time of the Scithon; composite performance issues at extreme temperatures, limited durability against UV exposure and space radiation, and chemical resistance issues with rocket fuels. Over the course of the Scithon researchers uncovered hundreds of papers to support their claims around creating reusable rockets. One of the conclusions reached suggested that nanostructured coatings provide better high-temperature performance and corrosion protection, based on this paper on the development of radiation shielding of composite space enclosures as a core element of their solution.
The Falcon X launch was supported by multitudes of research, some of which is similar to the conclusions of the Scithon teams. Two factors aiding to the success of the mission were the ability to quantify the catalytic properties of reusable thermal elements and simulating data for the design of high-temperature composites, method designed by NASA. And both of these principles relate to the conclusions reached by one of the Scithon teams.
The success of Falcon X coupled with the Sciton results argues that using Iris.AI individuals with no direct background expertise were also able to conduct innovative and groundbreaking research, often reaching similar conclusions to those of dedicated scientists, engineers, and researchers.