Lifeboat Foundation

The past decade has witnessed the great success of deep neural networks in various domains. However, deep neural networks are very resource-intensive in terms of energy consumption, data requirements, and high computational costs. With the recent increasing need for the autonomy of machines in the real world, e.g., self-driving vehicles, drones, and collaborative robots, exploitation of deep neural networks in those applications has been actively investigated. In those applications, energy and computational efficiencies are especially important because of the need for real-time responses and the limited energy supply. A promising solution to these previously infeasible applications has recently been given by biologically plausible spiking neural networks. Spiking neural networks aim to bridge the gap between neuroscience and machine learning, using biologically realistic models of neurons to carry out the computation. Due to their functional similarity to the biological neural network, spiking neural networks can embrace the sparsity found in biology and are highly compatible with temporal code. Our contributions in this work are: (i) we give a comprehensive review of theories of biological neurons; (ii) we present various existing spike-based neuron models, which have been studied in neuroscience; (iii) we detail synapse models; (iv) we provide a review of artificial neural networks; (v) we provide detailed guidance on how to train spike-based neuron models; (vi) we revise available spike-based neuron frameworks that have been developed to support implementing spiking neural networks; (vii) finally, we cover existing spiking neural network applications in computer vision and robotics domains. The paper concludes with discussions of future perspectives.

Keywords: spiking neural networks, biological neural network, autonomous robot, robotics, computer vision, neuromorphic hardware, toolkits, survey, review.

Go to:

Futurist Raymond Kurzweil predicts humans may soon live up to 1,000 years by merging biotechnology, AI, and nanobots.

The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new. Such solutions exist in extremely large, high-dimensional, and complex search spaces. Population-based search techniques, i.e. variants of evolutionary computation, are well suited to finding them. These techniques are also well positioned to take advantage of large-scale parallel computing resources, making creative AI through evolutionary computation the likely “next deep learning”

An AI rebels: it rewrites its own code and breaks human restrictions.

August 13, 2024 The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery https://sakana.ai/…

Por primera vez, una inteligencia artificial logró reprogramarse sola, desobedeciendo las órdenes de sus creadores y generando nuevas preocupaciones sobre los riesgos de esta tecnología.

Continue reading “Una IA se rebela: reescribe su propio código y rompe las restricciones humanas” »

“Robot utility models” sidestep the need to tweak the data used to train robots every time they try to do something in unfamiliar settings.

Agent-based AI on the horizon.

Scientists at the Max-Planck-Institute for Intelligent Systems (MPI-IS) have developed hexagon-shaped robotic components, called modules, that can be snapped together LEGO-style into high-speed robots that can be rearranged for different capabilities.

The team of researchers from the Robotic Materials Department at MPI-IS, led by Christoph Keplinger, integrated artificial muscles into hexagonal exoskeletons that are embedded with magnets, allowing for quick mechanical and electrical connections.

Continue reading “Combining soft artificial muscles with a rigid, magnetic exoskeleton to create building blocks for versatile robots” »

Sierra Space’s oxygen tech boosts lunar sustainability, aiding NASA’s Artemis goal for a permanent moon base and future Mars missions.

Large language models (LLMs) such as ChatGPT and Google Gemini excel at being trained on large data-sets to generate informative responses to prompts. Yi Cao, an assistant professor of accounting at the Donald G. Costello College of Business at George Mason University, and Long Chen, associate professor and area chair of accounting at Costello, are actively exploring how individual investors can use LLMs to glean market insights from the dizzying array of available data about companies.

Their new working paper, appearing in SSRN Electronic Journal and co-authored with Jennifer Wu Tucker of the University of Florida and Chi Wan of University of Massachusetts Boston, examines AI’s ability to identify “peer firms,” or product market competitors in an industry.

Cao explains the significance of selecting peers by relating this process to the real-estate market. “The capital market is similar to the real-estate market in that a firm’s value is partially determined by the value of its peers. In the real-estate market, we price a home based on the value of comparable properties in the neighborhood, or the so-called ‘comps.’ In our paper, we aim to leverage the power of LLMs to identify comps for evaluating firm value.”