Artificial Neural Networks Archives

New Deep Learning Models: Fewer Neurons, More Intelligence

Posted by Admin | Oct 14, 2020 | Artificial Neural Networks |

Artificial intelligence (AI) can become more efficient and reliable if it is made to mimic...

Teaching Physics to Neural Networks Removes ‘Chaos Blindness’

Posted by Admin | Jul 12, 2020 | Artificial Neural Networks |

Researchers from North Carolina State University have discovered that teaching physics to neural...

Thousands of artificial synapses on a single chip

Posted by Admin | Jun 9, 2020 | Artificial Neural Networks, Computing |

MIT engineers have designed a “brain-on-a-chip,” smaller than a piece of confetti, that is made...

Sensors made with neural networks can recognize images in nanoseconds

Posted by Age of Robots | Apr 14, 2020 | Artificial Neural Networks |

An ultra-fast image sensor with a built-in neural network has been developed at TU Wien (Vienna). It can be trained to recognize certain objects. It has now been presented in “Nature”.

Nanoelectrodes record thousands of connected mammalian neurons from inside

Posted by Admin | Sep 24, 2019 | Artificial Neural Networks |

How our brain cells, or neurons, use electrical signals to communicate and coordinate for higher...

Researchers Move Closer to Completely Optical Artificial Neural Network

Posted by Age of Robots | Aug 7, 2018 | Artificial Neural Networks |

Researchers have shown that it is possible to train artificial neural networks directly on an optical chip.

Test Tube Artificial Neural Network Recognizes “Molecular Handwriting”

Posted by Age of Robots | Jul 16, 2018 | Artificial Neural Networks |

Test tube chemistry using synthetic DNA molecules can be utilized in complex computing tasks to exhibit artificial intelligence.

Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction

Posted by Age of Robots | Apr 4, 2018 | Artificial Neural Networks |

A research team led by associate professor Eiji Watanabe of the National Institute for Basic Biology successfully reproduced illusory motion by DNNs trained for prediction.