'Lucy' probably needed to watch her back. Researchers led by the University of Iowa have described and named a new crocodile species that roamed a region in Africa more than 3 million years ago. The species is named Lucy's hunter, because it overlapped with the famed Lucy and her hominin kin and would have hunted them. Breakthroughs, discoveries, and DIY tips sent six days a week. Humans have contended with crocodiles for a long time.

Can neural networks systematically capture discrete, compositional task structure despite their continuous, distributed nature? The impressive capabilities of large-scale neural networks suggest that the answer to this question is yes. However, even for the most capable models, there are still frequent failure cases that raise doubts about their compositionality. Here, we seek to understand what it takes for a standard neural network to generalize over tasks that share compositional structure. We find that simply scaling data and model size leads to compositional generalization. We show that this holds across different task encodings as long as the training distribution sufficiently covers the task space. In line with this finding, we prove that standard multilayer perceptrons can approximate a general class of compositional task families to arbitrary precision using only a linear number of neurons with respect to the number of task modules. Finally, we uncover that if networks successfully compositionally generalize, the constituents of a task can be linearly decoded from their hidden activations. We show that this metric correlates with failures of text-to-image generation models to compose known concepts.

'Joaquinraptor casali' was one of the Cretaceous Era's last apex predators. Breakthroughs, discoveries, and DIY tips sent every weekday. Paleontologists have discovered a carnivorous dinosaur in central Patagonia that they believe occupied the top of the Late Cretacean food chain. For additional proof, they point to its likely final meal. According to new analysis published on September 23 in the journal, appears to have died with an ancient, nearly 8-inch-long crocodile leg next to its jaws.

LLMs are frequently used tools for conversational generation. Without additional information LLMs can generate lower quality responses due to lacking relevant content and hallucinations, as well as the perception of poor emotional capability, and an inability to maintain a consistent character. Knowledge graphs are commonly used forms of external knowledge and may provide solutions to these challenges. This paper introduces three proposals, utilizing knowledge graphs to enhance LLM generation. Firstly, dynamic knowledge graph embeddings and recommendation could allow for the integration of new information and the selection of relevant knowledge for response generation. Secondly, storing entities with emotional values as additional features may provide knowledge that is better emotionally aligned with the user input. Thirdly, integrating character information through narrative bubbles would maintain character consistency, as well as introducing a structure that would readily incorporate new information.

POMDP planning faces two major computational challenges: large state spaces and long planning horizons. The recently introduced Monte Carlo Value Iteration (MCVI) can tackle POMDPs with very large discrete state spaces or continuous state spaces, but its performance degrades when faced with long planning horizons. This paper presents Macro-MCVI, which extends MCVI by exploiting macro-actions for temporal abstraction. We provide sufficient conditions for Macro-MCVI to inherit the good theoretical properties of MCVI. Macro-MCVI does not require explicit construction of probabilistic models for macro-actions and is thus easy to apply in practice. Experiments show that Macro-MCVI substantially improves the performance of MCVI with suitable macro-actions.

But have you ever wondered what a fight between a hippopotamus and a great white shark might look like? Now, scientists have set the record straight, after using artificial intelligence (AI) to simulate battles between the most terrifying animals on Earth. Somewhat surprisingly, the simulations suggest that a hippo would beat a great white shark - and could even take down a polar bear. However, the ultimate champion of the animal kingdom is the African Elephant, according to researchers from Animal Matchup. In honour of World Animal Day, experts from Animal Match set out to settle the debate - which animal is the strongest?

Noun compound interpretation is the task of expressing a noun compound (e.g. chocolate bunny) in a free-text paraphrase that makes the relationship between the constituent nouns explicit (e.g. bunny-shaped chocolate). We propose modifications to the data and evaluation setup of the standard task (Hendrickx et al., 2013), and show that GPT-3 solves it almost perfectly. We then investigate the task of noun compound conceptualization, i.e. paraphrasing a novel or rare noun compound. E.g., chocolate crocodile is a crocodile-shaped chocolate. This task requires creativity, commonsense, and the ability to generalize knowledge about similar concepts. While GPT-3's performance is not perfect, it is better than that of humans -- likely thanks to its access to vast amounts of knowledge, and because conceptual processing is effortful for people (Connell and Lynott, 2012). Finally, we estimate the extent to which GPT-3 is reasoning about the world vs. parroting its training data. We find that the outputs from GPT-3 often have significant overlap with a large web corpus, but that the parroting strategy is less beneficial for novel noun compounds.

Time will tell if AI decides to wipe out humanity in a terminator-style total war. In the meantime, MailOnline Travel decided to harness its power for good – and ask it for advice about surviving a multitude of perils, from a plane crash to a volcanic eruption, and from attacks by bees and crocodiles to a sinking ship. Mostly useful, though some may find the suggestion to'get away from the bees' stating the very obvious. Google Bard's plane crash advice includes avoiding sitting in the first few rows, as'these rows are more likely to be damaged in a crash' They are trained to handle emergency situations and will know what to do. This will help to keep you in your seat during the crash. This position will help to protect your head and neck in the event of a crash. To assume the brace position, place your feet flat on the floor, lean forward, and place your head down on your knees. It is important to stay calm in an emergency situation.

Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! Our thoughts are private – or at least they were. New breakthroughs in neuroscience and artificial intelligence are changing that assumption, while at the same time inviting new questions around ethics, privacy, and the horizons of brain/computer interaction. Research published last week from Queen Mary University in London describes an application of a deep neural network that can determine a person's emotional state by analyzing wireless signals that are used like radar.

As a good battle shonen should, One Piece has a variety of iconic fights that are complemented by some flashy and exciting finishing moves. A staple of any anime fight, the idea of the finishing move fuses both brutal power and explicit branding to create some of the most exciting and recognizable attacks ever seen in fiction. In One Piece's world, Devil Fruits, Haki, martial arts, robotic enhancements, and some very loose interpretations of physics all contribute to One Piece's own, colorful gallery of finishing moves. And while rating each one's power and effectiveness is a large discussion within its own right, it's also really fun just looking at which finishing moves are just the coolest and most memorable. Monkey D. Luffy's Gum-Gum Gatling doesn't have the awe-inspiring, simplistic appeal of a one-hit attack; but what it lacks in brevity, it more than makes up for with raw, visceral spectacle.