We address the problem of incremental semantic segmentation (ISS) recognizing novel object/stuff categories continually without forgetting previous ones that have been learned. The catastrophic forgetting problem is particularly severe in ISS, since pixel-level ground-truth labels are available only for the novel categories at training time. To address the problem, regularization-based methods exploit probability calibration techniques to learn semantic information from unlabeled pixels. While such techniques are effective, there is still a lack of theoretical understanding of them. Replay-based methods propose to memorize a small set of images for previous categories.

We then compute the gradient of CKD w.r.t z

We address the problem of incremental semantic segmentation (ISS) recognizing novel object/stuff categories continually without forgetting previous ones that have been learned. The catastrophic forgetting problem is particularly severe in ISS, since pixel-level ground-truth labels are available only for the novel categories at training time. To address the problem, regularization-based methods exploit probability calibration techniques to learn semantic information from unlabeled pixels. While such techniques are effective, there is still a lack of theoretical understanding of them. Replay-based methods propose to memorize a small set of images for previous categories.

Artificial Life (ALife) as an interdisciplinary field draws inspiration and influence from a variety of perspectives. Scientific progress crucially depends, then, on concerted efforts to invite cross-disciplinary dialogue. The goal of this paper is to revitalize discussions of potential connections between the fields of Computational Creativity (CC) and ALife, focusing specifically on the concept of Open-Endedness (OE); the primary goal of CC is to endow artificial systems with creativity, and ALife has dedicated much research effort into studying and synthesizing OE and artificial innovation. However, despite the close proximity of these concepts, their use so far remains confined to their respective communities, and their relationship is largely unclear. We provide historical context for research in both domains, and review the limited work connecting research on creativity and OE explicitly. We then highlight specific questions to be considered, with the eventual goals of (i) decreasing conceptual ambiguity by highlighting similarities and differences between the concepts of OE and creativity, (ii) identifying synergy effects of a research agenda that encompasses both concepts, and (iii) establishing a dialogue between ALife and CC research.

Large Language Models (LLMs) have taken the field of AI by storm, but their adoption in the field of Artificial Life (ALife) has been, so far, relatively reserved. In this work we investigate the potential synergies between LLMs and ALife, drawing on a large body of research in the two fields. We explore the potential of LLMs as tools for ALife research, for example, as operators for evolutionary computation or the generation of open-ended environments. Reciprocally, principles of ALife, such as self-organization, collective intelligence and evolvability can provide an opportunity for shaping the development and functionalities of LLMs, leading to more adaptive and responsive models. By investigating this dynamic interplay, the paper aims to inspire innovative crossover approaches for both ALife and LLM research. Along the way, we examine the extent to which LLMs appear to increasingly exhibit properties such as emergence or collective intelligence, expanding beyond their original goal of generating text, and potentially redefining our perception of lifelike intelligence in artificial systems.

Alife Health, the fertility technology company building artificial intelligence tools to advance in-vitro fertilization (IVF), announced today it has raised $22 million in Series A financing co-led by existing Seed lead Deena Shakir at Lux Capital, and new investors Rebecca Kaden at Union Square Ventures and Anarghya Vardhana at Maveron, both of whom will also be joining Alife's Board of Directors. Alife's mission is to enhance IVF clinical decision-making with personalized, data-driven patient insights, ultimately helping clinicians maximize each patient's chances of success while lowering costs and barriers to access. Today, the 180 million people around the world who struggle with infertility face treatment options that are both expensive and inaccessible. The average IVF cycle can cost up to $25,000 in the U.S., and patients typically go through 3 to 5 cycles to have a baby. Successful pregnancies from IVF rely on a complex set of clinical decisions to deliver the optimal care for each patient.

Today, 1 in 8 couples struggle with infertility, and the treatment options they have access to are both expensive, as well as inaccessible: according to the National Conference of State Legislatures, in-vitro fertilization cycles can cost anywhere from $12,000 to $17,000, and that doesn't include medication; when medication is added in, the cost can be double to around $25,000. And many patients don't just go through one cycle, but three to five cycles on average in order to have a successful pregnancy In order to help break through all of these difficulties, inefficiencies, and barriers to access, Alife Health, which announced a $22 million Series A round of funding on Tuesday, is trying a new approach: artificial intelligence. "We believe AI has tremendous potential to impact the effectiveness and equity of fertility care," said Paxton Maeder-York, Alife's CEO and founder. "Our team has worked tirelessly to construct one of the largest and most diverse IVF datasets from top fertility clinics around the world." The company's AI uses pattern recognition to analyze this data and determine correlations between treatments and positive outcomes.

How can femtech enhance women's special journey to delivery? How can it help them start that journey when they're having difficulties in conceiving? A common understatement that you may hear these days is that the world has been affected by the Pandemic. Let's get something straight, the world has not merely been "affected" by the Pandemic, it has completely transformed, or let's say, tele-transformed. The Pandemic has had an obscene amount of negative consequences on the world, yet, dare we say it, there are a few players that have somewhat benefitted from the situation, players that encourage and believe in virtual, digitally-powered transactions.

Concepts similar to emergence have been used since antiquity, but we lack an agreed definition of emergence. Still, emergence has been identified as one of the features of complex systems. Most would agree on the statement "life is complex". Thus, understanding emergence and complexity should benefit the study of living systems. It can be said that life emerges from the interactions of complex molecules. But how useful is this to understand living systems? Artificial life (ALife) has been developed in recent decades to study life using a synthetic approach: build it to understand it. ALife systems are not so complex, be them soft (simulations), hard (robots), or wet (protocells). Then, we can aim at first understanding emergence in ALife, for then using this knowledge in biology. I argue that to understand emergence and life, it becomes useful to use information as a framework. In a general sense, emergence can be defined as information that is not present at one scale but is present at another scale. This perspective avoids problems of studying emergence from a materialistic framework, and can be useful to study self-organization and complexity.

Olaf Witkowski is the Chief Scientist at Cross Labs, which aims to bridge the divide between intelligence science and AI technology. A researcher of artificial life, Witkowski started in artificial intelligence by exploring the replication of human speech through machines. He founded Commentag in 2007, and in 2009 moved to Japan to continue research, where he first became interested in artificial life. In his own words, Witkowski says, "artificial intelligence means that you are trying to copy human intelligence as best as possible. Artificial life says, okay, that's good, but let's try to understand human intelligence and recreate it from the fundamental knowledge we have acquired. It's a bit like the Richard Feynman quote: what I cannot create, I do not understand."