This new AI-powered drone can resist strong winds and continue its flight thanks to a deep-learning technique created by Caltech engineers.
Category: robotics/AI – Page 1276
A new artificial intelligence algorithm called ‘Zoobot’ helped to identify 40,000 ring galaxies. What else is the astronomical AI capable of?
A machine-learning algorithm that includes a quantum circuit generates realistic handwritten digits and performs better than its classical counterpart.
Machine learning allows computers to recognize complex patterns such as faces and also to create new and realistic-looking examples of such patterns. Working toward improving these techniques, researchers have now given the first clear demonstration of a quantum algorithm performing well when generating these realistic examples, in this case, creating authentic-looking handwritten digits [1]. The researchers see the result as an important step toward building quantum devices able to go beyond the capabilities of classical machine learning.
The most common use of neural networks is classification—recognizing handwritten letters, for example. But researchers increasingly aim to use algorithms on more creative tasks such as generating new and realistic artworks, pieces of music, or human faces. These so-called generative neural networks can also be used in automated editing of photos—to remove unwanted details, such as rain.
AI & Machine Learning (ML) Course Online — BlackBelt Plus Program
Certified AI & ML BlackBelt Plus Program is the best data science course online to become a globally recognized data scientist. BlackBelt Plus Program includes 105+ detailed (1:1) mentorship sessions, 36 + assignments, 50+ projects, learning 17 Data Science tools including Python, Pytorch, Tableau, Scikit Learn, Power BI, Numpy, Spark, Dask, Feature Tools, Keras, Matplotlib, Rasa, Pandas, ML Box, Scikits-Image, Amazon SageMaker, Streamlit, AWS, Flask, and other technologies such as Computer Vision, Natural Language Processing, Machine Learning, Artificial Intelligence and Deep Learning.
By Planning in the Latent Space of a Learned World Model. The world model Director builds from pixels allows effective planning in a latent space. To anticipate future model states given future actions, the world model first maps pictures to model states. Director optimizes two policies based on the model states’ anticipated trajectories: Every predetermined number of steps, the management selects a new objective, and the employee learns to accomplish the goals using simple activities. The direction would have a difficult control challenge if they had to choose plans directly in the high-dimensional continuous representation space of the world model. To reduce the size of the discrete codes created by the model states, they instead learn a goal autoencoder. The goal autoencoder then transforms the discrete codes into model states and passes them as goals to the worker after the manager has chosen them.
Deep reinforcement learning advancements have accelerated the study of decision-making in artificial agents. Artificial agents may actively affect their environment by moving a robot arm based on camera inputs or clicking a button in a web browser, in contrast to generative ML models like GPT-3 and Imagen. Although artificial intelligence has the potential to aid humans more and more, existing approaches are limited by the necessity for precise feedback in the form of often given rewards to acquire effective techniques. For instance, even robust computers like AlphaGo are restricted to a certain number of moves before earning their next reward while having access to massive computing resources.
Contrarily, complex activities like preparing a meal necessitate decision-making at all levels, from menu planning to following directions to the shop to buy supplies to properly executing the fine motor skills required at each stage along the way based on high-dimensional sensory inputs. Artificial agents can complete tasks more independently with scarce incentives thanks to hierarchical reinforcement learning (HRL), which automatically breaks down complicated tasks into achievable subgoals. Research on HRL has, however, been difficult because there is no universal answer, and existing approaches rely on manually defined target spaces or subtasks.
The bottomless bucket is Karl Marx’s utopian creed: “From each according to his ability, to each according to his needs.” In this idyllic world, everyone works for the good of society, with the fruits of their labor distributed freely — everyone taking what they need, and only what they need. We know how that worked out. When rewards are unrelated to effort, being a slacker is more appealing than being a worker. With more slackers than workers, not nearly enough is produced to satisfy everyone’s needs. A common joke in the Soviet Union was, “They pretend to pay us, and we pretend to work.”
In addition to helping those who in the great lottery of life have drawn blanks, governments should adopt myriad policies that expand the economic pie, including education, infrastructure, and the enforcement of laws and contracts. Public safety, national defense, dealing with externalities are also important. There are many legitimate government activities and there are inevitably tradeoffs. Governing a country is completely different from playing a simple, rigged distribution game.
I love computers. I use them every day — not just for word processing but for mathematical calculations, statistical analyses, and Monte Carlo simulations that would literally take me several lifetimes to do by hand. Computers have benefited and entertained all of us. However, AI is nowhere near ready to rule the world because computer algorithms do not have the intelligence, wisdom, or commonsense required to make rational decisions.
An innovative new collaboration between EPFL’s HexHive Laboratory and Oracle has developed automated, far-reaching technology in the ongoing battle between IT security managers and attackers, hoping to find bugs before the hackers do.
On the 9th of December 2021 the world of IT security went into a state of shock. Before its developers even knew it, the log4j application—part of the Apache suite used on most web servers—was being exploited by hackers, allowing them to take control of servers and data centers all over the world.
The Wall Street Journal reported news that nobody wanted to hear: “U.S. officials say hundreds of millions of devices are at risk. Hackers could use the bug to steal data, install malware or take control.”
It’s not that the particular labelers didn’t do a good job, it’s that they were given an impossible task.
There are no shortcuts to gleaning insight into human communications. We’re not stupid like machines are. We can incorporate our entire environment and lived history into the context of our communications and, through the tamest expression of our masterful grasp on semantic manipulation, turn nonsense into philosophy (shit happens) or turn a truly mundane statement into the punchline of an ageless joke (to get to the other side).
What these Google researchers have done is spent who knows how much time and money developing a crappy digital version of a Magic 8-Ball. Sometimes it’s right, sometimes it’s wrong, and there’s no way to be sure one way or another.
Judges must now consult the AI on every case by law, Beijing’s Supreme Court said in an update on the system published this week, and if they go against its recommendation they must submit a written explanation for why.
The AI has also been connected to police databases and China’s Orwellian social credit system, handing it the power to punish people — for example by automatically putting a thief’s property up for sale online.
Beijing has hailed the new technology for making ‘a significant contribution to the judicial advancement of human civilisation’ — while critics say it risks creating a world in which man is ruled by machine.
A DeepMind research group conducted a comprehensive generalization study on neural network architectures in the paper ‘Neural Networks and the Chomsky Hierarchy’, which investigates whether insights from the theory of computation and the Chomsky hierarchy can predict the actual limitations of neural network generalization.
While we understand that developing powerful machine learning models requires an accurate generalization to out-of-distribution inputs. However, how and why neural networks can generalize on algorithmic sequence prediction tasks is unclear.
The research group performed a thorough generalization study on more than 2000 individual models spread across 16 tasks of cutting-edge neural network architectures and memory-augmented neural networks on a battery of sequence-prediction tasks encompassing all tiers of the Chomsky hierarchy that can be evaluated practically with finite-time computation.