Get Started for FREE
Sign up with Facebook Sign up with X
I don't have a Facebook or a X account
 Your new post is loading...
Your new post is loading...
Scoop.it!
A simple guide to reinforcement learning for a complete beginner. The blog includes definitions with examples, real-life applications, key concepts, and various types of learning resources. 
No comment yet.
Sign up to comment
Scoop.it!
AI is sending up the Bat-signal and synthetic data is answering the call for more robust, powerful, and less-biased AI systems.
Phillip Trotter's insight:
Not sure about the batman link - but interesting article on use of synthetic data. At Symbol we use simulations to generate synthetic data sets for some of our AI training and it makes otherwise impossible tasks possible. Good intro article.
Scoop.it!
Deep-learning algorithms such as AlphaFold2 and RoseTTAFold can now predict a protein’s 3D shape from its linear sequence — a huge boon to structural biologists. Via Gerd Moe-Behrens
Scoop.it!
Complex systems may have billion components making consensus formation slow and difficult. Recently several overlapping stories emerged from various disciplines, including protein structures, neuroscience and social networks, showing that fast responses to known stimuli involve a network core of few, strongly connected nodes. In unexpected situations the core may fail to provide a coherent response, thus the stimulus propagates to the periphery of the network. Here the final response is determined by a large number of weakly connected nodes mobilizing the collective memory and opinion, i.e. the slow democracy exercising the 'wisdom of crowds'. This mechanism resembles to Kahneman's "Thinking, Fast and Slow" discriminating fast, pattern-based and slow, contemplative decision making. The generality of the response also shows that democracy is neither only a moral stance nor only a decision making technique, but a very efficient general learning strategy developed by complex systems during evolution. The duality of fast core and slow majority may increase our understanding of metabolic, signaling, ecosystem, swarming or market processes, as well as may help to construct novel methods to explore unusual network responses, deep-learning neural network structures and core-periphery targeting drug design strategies.
Fast and slow thinking -- of networks: The complementary 'elite' and 'wisdom of crowds' of amino acid, neuronal and social networks http://arxiv.org/abs/1511.01238 ; Via Complexity Digest
Complexity Digest's curator insight,
November 18, 2015 6:13 PM
See Also: http://networkdecisions.linkgroup.hu 
António F Fonseca's curator insight,
November 23, 2015 3:30 AM
Interesting paper about fast cores and slow periphery, conflict in the elite vs democratic consensus. 
Marcelo Errera's curator insight,
November 24, 2015 11:32 AM
Yes, there must be few fasts and many slows. It's been predicted by CL in many instances.
http://www.researchgate.net/publication/273527384_Constructal_Law_Optimization_as_Design_Evolution
Scoop.it!
A new theory can explain the formation of swarming patterns observed in ensembles of self-propelled polar particles. Via Eugene Ch'ng
Eugene Ch'ng's curator insight,
April 13, 2014 8:27 AM
How do individual animals form swarms, schools, and flocks? In the 1990s, physicists modeled collections of self-propelled particles (so-called “active matter”) and could simulate the ordering that occurs in animal flocks. Theoretical models have reproduced many aspects of this collective behavior, but a number of questions have persisted. One concerns the observation that in polar, active matter—think of a collection of small, mutually interacting swimming arrows—the particles organize themselves into three possible pattern classes: density waves, solitary waves (solitons), and traveling “droplets.” No single theory has been able to explain the formation and diversity of these patterns. However, in a paper in Physical Review Letters, Jean-Baptiste Caussin and collaborators from institutes in France, Germany, and the Netherlands, have solved a hydrodynamic model of polar active particles and have accounted for the origin and variety of these propagating swarm structures...
Scoop.it!
The next big ideas from 'Idea Man' Paul Allen: AI and cell biology NBCNews.com Software billionaire Paul Allen is already using his riches to further brain science, spaceflight, rock 'n' roll history — and oh, the Seattle Seahawks, too — but he's...
Phillip Trotter's insight:
Paul Allen. who has funded a lot of important research over the years - recently announced the funding of a new Aritificial Intelligence research center in Seattle. The Paul Allen Artificial Intelligence Institute will be headed by Oren Etzioni, formerly head of the University of Washington's Computer Science Department, where he was the Washington Research Foundation Entrepreneurship Professor and Director of the Turing Center. The new AI center is a compliments to Paul Allen's $400 million neuroscience research center also in Seattle.
Scoop.it!
Dr. Arend Hintze E-mail: ude.usmnull@eztnih CV Well, I am looking for a job – a faculty position to be exact.
Phillip Trotter's insight:
Usually don't post job info here - but I loved the picture and Arend Hintze is one of the alife's rising stars who's research papers are insightful. If you or your research team are looking for a proven experienced post doc for an innovative AI research group - email him.
Scoop.it!
From
arxiv
Networks of interconnected nodes have long played a key role in cognitive science, from artificial neural networks to spreading activation models of semantic memory. Recently, however, a new Network Science has been developed, providing insights into the emergence of global, system-scale properties in contexts as diverse as the Internet, metabolic reactions or collaborations among scientists. Today, the inclusion of network theory into cognitive sciences, and the expansion of complex systems science, promises to significantly change the way in which the organization and dynamics of cognitive and behavioral processes are understood. In this paper, we review recent contributions of network theory at different levels and domains within the cognitive sciences.
Networks in Cognitive Science Andrea Baronchelli, Ramon Ferrer-i-Cancho, Romualdo Pastor-Satorras, Nick Chater, Morten H. Christiansen http://arxiv.org/abs/1304.6736 Via Complexity Digest
Phillip Trotter's insight:
Network and complex systems theory are becoming key cornerstones to many fields, and this paper helps explain the mapping to cognitive sciences. Worth a read.
Jim Price's curator insight,
May 24, 2013 12:56 PM
A reminder that complex systems theory is all about scalability (fractals for instance) and that the ways of working of the brain in cognitive science can offer clincial teachers lessons about how we teach in other contexts - both the classroom & workplace. Just 'think' about it...!
Scoop.it!
Scientists find further evidence that crabs and other crustaceans feel pain and then take steps to avoid it.
Phillip Trotter's insight:
While perhaps unlikely to change food industry and eating habits in the short term, I suspect as we develop more understanding of sensory systems and related perception mechanisms our understanding of sentience and animal perception is going to go through a radical overhall in the coming decade.
Scoop.it!
What’s the difference between machine learning, deep learning, big data, statistics, decision & risk analysis, probability, fuzzy logic, and all the rest? None, except for terminology. William Briggs gives a masterclass in explaining terminology currently bounding through the worlds of big data, analytics and data. Worth reading.
Scoop.it!
Intersting article by John Markoff on artificial neural networks and learning theorems and big data problems. Using an artificial intelligence technique inspired by theories about how the brain recognizes patterns, technology companies are reporting startling gains in fields as diverse as computer vision, speech recognition and the identification of new molecules... Click on the title to learn more.
Scoop.it!
Long but interesting interview with linguist Noam Chomsky fom the Atlantic, on A.I. Wether you agree or disagree with his views on computation and intelligence and the directions taken by AI community and neuroscience - it makes for a stimulating read. Click on the image or the title to learn more.
Scoop.it!
Health care in the United States certainly needs an overhaul. The question is whether that overhaul will come from artificially intelligent doctors. IBM has launched partnerships with insurance giant WellPoint and the Sloan-Kettering Cancer Center in New York and is expected offer Watson commercially to hospitals within the next few years. Wired article discusses the approach and pros and cons as seen by some doctors. Worth a read for a quick intro to modern AI comprising data mining and big data topics as an approach to treatment diagnostics in healthcare. Click on the image or the title to learn more.
|
Scoop.it!
Hugging Face has released a free course on Deep RL. It is self-paced and shares a lot of pointers on theory, tutorials, and hands-on guides.
Phillip Trotter's insight:
WE do a fair bit of reinforcement learning at Symbol Research so it is always good to come across useful resources we can recommend. HuggingFace make a lot of deep learning models easily accessible and recently launched a new RL training course. From a glance it looks similar to courses available from Udacity and others - but if you are looking for a course, with an easy to use Python API - HuggingFace will be a good starting point. Recommended.
Scoop.it!
Browse the GTC conference catalog of sessions, talks, workshops, and more.
Phillip Trotter's insight:
The good folks at NVIDIA have made the recent 324 GTC conference sessions freely available. With topics like Omniverse, Bots, Digital Twins, Autonomous Vehicles and extensive applications of AI , visualization and simulation from experts around the world. They are worth watching and investigating. Enjoy (and thanks NVIDIA!!)
Scoop.it!
Scientists are exploring a mysterious pattern, found in birds’ eyes, boxes of marbles and other surprising places, that is neither regular nor random.
Phillip Trotter's insight:
If you want to understand why AI is beginning to make major breakthroughts - it helps to understand the physics underpinning our world. This article gives a good overview of one such physical property - hyperuniform that is neither regular or random but a distribution that reflects the constrained reality that biological systems evolve within. Very much worth reading.
Scoop.it!
Accessing information efficiently is vital for animals to make the optimal decisions, and it is particularly important when they are facing predators. Yet until now, very few quantitative conclusions have been drawn about the information dynamics in the interaction between animals due to the lack of appropriate theoretic measures. Here, we employ transfer entropy (TE), a new information-theoretic and model-free measure, to explore the information dynamics in the interaction between a predator and a prey fish. We conduct experiments in which a predator and a prey fish are confined in separate parts of an arena, but can communicate with each other visually and tactilely. TE is calculated on the pair’s coarse-grained state of the trajectories. We find that the prey’s TE is generally significantly bigger than the predator’s during trials, which indicates that the dominant information is transmitted from predator to prey. We then demonstrate that the direction of information flow is irrelevant to the parameters used in the coarse-grained procedures. We further calculate the prey’s TE at different distances between it and the predator. The resulted figure shows that there is a high plateau in the mid-range of the distance and that drops quickly at both the near and the far ends. This result reflects that there is a sensitive space zone where the prey is highly vigilant of the predator’s position.
Information Dynamics in the Interaction between a Prey and a Predator Fish Entropy 2015, 17(10), 7230-7241; http://dx.doi.org/10.3390/e17107230 ; Via Complexity Digest, Phillip Trotter
Phillip Trotter's insight:
Interesting use of entropy for information transfer in predator-prey interactions. Good paper - worth reading and a lot worth thinking further about.
Scoop.it!
My preferred job title is 'theorist', but that is often too ambiguous in casual and non-academic conversation, so I often settle for 'computer scientist'. Unfortunately, it seems that the overwhelming majority of people equate ...
Phillip Trotter's insight:
Artem Kaznatcheev, a researcher in theoretical computer science - i.e. the ideas that underpin computing - has a wonderful write up of Stephanie Forrest's Stannislaw Ulam lecture at the SFI on using inspiration from Biology to address challenges in Software industry. The Ulam lecture is available in video - but its a few hours long - through seriously worth watching and covers modern developments in genetic programming and other approaches. If you need an abbrieviated write up of the key ideas underpinning the Professor Forrest's lecture - then Artem's write up is an awesomely succinct. Worth reading (and the lectures linked in his article - are worth watching!)
Scoop.it!
ECAL 2013, the twelfth European Conference on Artificial Life, presents the current state of the art of a mature and autonomous discipline collocated at the intersection of a theoretical perspective (the scientific explanations of different levels of life organizations, e.g., molecules, compartments, cells, tissues, organs, organisms, societies, collective and social phenomena) and advanced technological applications (bio-inspired algorithms and techniques to building-up concrete solutions such as in robotics, data analysis, search engines, gaming).
Advances in Artificial Life, ECAL 2013 Proceedings of the Twelfth European Conference on the Synthesis and Simulation of Living Systems Edited by Pietro Liò, Orazio Miglino, Giuseppe Nicosia, Stefano Nolfi and Mario Pavone http://mitpress.mit.edu/books/advances-artificial-life-ecal-2013 Via Complexity Digest
Phillip Trotter's insight:
I have a big soft spot for artificial life research - partly because i was a young researcher shortly after Chris Langton coined the term and a lot of my early hacking was around games of life, vants and cellular automata but also because over the years I have found many of the techniques discussed in ALIFE circles applicable to other fields such as machine learning, control architectures, and emergent simulation etc so this is definitely one for the reading list.
luiy's curator insight,
September 9, 2013 4:35 PM
About the Editors
Pietro Liò is Reader in Computational Biology at the University of Cambridge and a member of the Artificial Intelligence group of the University's Computer Laboratory. He researches on Predictive models in Personalized medicine and Multiscale modelling of molecules-cell-tissue-organ interactions.
Orazio Miglino is a full Professor of Psychology at University of Naples Federico II where he leads the Natural and Artificial Cognition Lab. He is also an associate researcher at the Institute of Cognitive Sciences and Technologies of Italian National Research Council (ISTC-CNR) in Rome.
Giuseppe Nicosia is an Associate Professor in Computational Systems and Synthetic Biology in the Dept. of Mathematics and Computer Science of the University of Catania, Italy. His research activities focus on the design of biological systems, neuroinformatics, system design, design automation, optimization, solar cells, circuit and semiconductor design.
Stefano Nolfi is Research Director at the Italian National Research Council (CNR), director of the Laboratory of Autonomous Robots and Artificial Life of the Institute of Cognitive Sciences and Technologies. His research activities focus on the evolution and development of behavioural and cognitive skills in natural and artificial embodied agents (robots).
Mario Pavone is an Assistant Professor in computer science at the Department of Mathematics and Computer Science of the University of Catania. He is co-founder of TaoScience Research center, and he is also a member of the EURO association (The Association of European Operational Research Societies)
Scoop.it!
In a general sense, a Markov Network Brain (MNB) implements a probabilistic finite state machine, and as such is a Hidden Markov Model (HMM). MNBs act as controllers and decision makers for agents ...
Phillip Trotter's insight:
If like me, you are old enough to remember the animals to animats proceedings from the early 1990's which detailed early researchon agent based modeling, reinforcement learning algorithms and autonomous robots using neural networks, genetic algorithms and other probabilistic finite state machines as control architectures this will be of interest. If you are not -try and find a copy and read up - since a lot of current research is based on early ideas presented in those proceedings. The Adamilab have produced a stable implementation and platform for hidden markov model based controllers for agent based models and robotics. Code is available on Github and the Markov Network Brains article gives a good overview of why its of interest and underlying reasoning behind the implementation for anyone working on agent based simulation and autonomous robot and sensor platforms.
Scoop.it!
Ingredients for the Semantic Sensor WebJožef Stefan InstituteLjubljana, SloveniaSeptember 23rd 2011Oscar CorchoFacultad de Inform
Phillip Trotter's insight:
Great presentation on semantic analysis of data captured by sensor networks by Oscar Corcho of the Jozef Stefan Institute, Slovenia.
Scoop.it!
Good inverview with Dr. Jürgen Schmidhuber, Director of the Swiss Artificial Intelligence Lab, IDSIA. His research team’s artificial neural networks (NNs) have won many international awards, and recently were the first to achieve human-competitive performance on various benchmark data sets. IDSIA are probably the current world leaders in ANN research and the quality of what they do is rather insipiring. worth reading.
Scoop.it!
Interesting article in The New York Times on Jeff Hawkins (of Palm computer fame) new company Numenta. Their Grok product uses a complex artificial neuron model to build predictive analytics from sensed data. Worth reading. Click on the image or the title to learn more.
Scoop.it!
Something scientists have come to understand is that slime molds are much smarter than they look. One species in particular, the SpongeBob SquarePants–yellow Physarum polycephalum, can solve mazes, mimic the layout of man-made transportation networks and choose the healthiest food from a diverse menu—and all this without a brain or nervous system. "Slime molds are redefining what you need to have to qualify as intelligent," Reid says. Via Dr. Stefan Gruenwald, Complexity Digest
Scoop.it!
Wired has an interesting article on mobile computing. As ARM seeks to put cell phone chips into our supercomputers, Intel is doing the reverse. The lines between the mobile hardware and data center hardware are blurring. Intel’s experimental Single-chip Cloud Computer project, or SCC is a 48 core chip acts as a “network” of processors on a single chip, with two cores per node. The nodes actually communicate to each other much the same way nodes in a cluster in a data center would. While these types of architectures are today used in big data applications that run on a server cloud environment there are actually many cases where a hybrid model would make the most sense including artificial intelligence, machine vision and augmented reality applications. Click on the image or the title to learn more.
|
Need a quick intro to Reinforcement Learning but don't have time to work though the HuggingFace course highlighted in our other post -then - take this quick primer from KDNuggets - and work through the related materials. You will be up to speed in no time. Recommended.