Artificial Neural Networks Memory

Uploading Memory.
The recurrent neutral network

I remember when I first watched this clip. I thought that, while it was impossible, it was nevertheless one of the coolest ideas ever.

Now is when neuroscience is starting to get scary cool.

Some of you might be thinking that I can’t be hinting that uploading memories into someone is within reality, but I am.

Researchers at the University of Southern California recently designed a cortical neural prosthesis (or an artificial neural system) for restoring or enhancing memory (Berger, Hampson, Song, Goonawardena, Marmarelis, & Deadwyler, 2011). This device isn’t a typical artificial neural network, but instead is a device that is capable of recording neural signals during a task and producing those signals itself once it has recorded them. In an experiment, this neural prosthesis recorded the activity of rats successfully completing a complex, trial-by-trial task that could not be done on the first try:

The behavioral testing apparatus for the DNMS [delayed-nonmatch-to-sample] task is the same as reported in prior studies (Deadwyler and Hampson 1997, 2004, Hampson et al 2008) and consists of a 43 × 43 × 50 cm Plexiglas chamber with two retractable levers (left and right) positioned on either side of a water trough on one wall of the chamber (figure 1). A photocell with a cue light activated nose-poke (NP) device was mounted in the center of the opposite wall. The chamber was housed inside a sound-attenuated cubicle. The DNMS task consisted of three phases: (1) sample phase: in which a single lever was presented randomly in either the left or right position; when the animal pressed the lever, the event was classified as sample response (SR), (2) delay phase: of variable duration (1–30 s) in which a nosepoke (NP) into a photocell was required to advance to the (3) nonmatch phase: in which both levers were presented and a response on the lever opposite to the SR, i.e., a nonmatch response (NR), was required for delivery of a drop of water (0.4 ml) in the trough. A response in the nonmatch phase on the lever in the same position as the SR (match response) constituted an ‘error’ with no water delivery and a turning off of the lights in the chamber for 5.0 s. Following the reward delivery (or an error) the levers were retracted for 10.0 s before the sample lever was presented to begin the next trial. Individual performance was assessed as % correct NRs with respect to the total number of trials (100–150) per daily (1–2 h) session.

Source: Some guy who thinks about thinking.

John Wiley & Sons Recursive Neural Networks for Associative Memory
Book (John Wiley & Sons)

You might also like:

Lec-6 Associative memory
Lec-6 Associative memory
Autoassociative temporal memory based on extended SRM0 neural network
Autoassociative temporal memory based on extended SRM0 neural network
.videorecognition.com/memory (Face Recognition using Associative Neural Network)
www.videorecognition.com/memory (Face Recognition using Associative Neural Network)

For anyone with an actual interest in AI

2008-03-02 20:38:48 by MsLoree

I found this book intresting:
Massively Parallel Artificial Intelligence
Edited by Hiroaki Kitano and James A. Hendler
"The increased sophistication and availability of massively parallel supercomputers has had two major impacts on research in artificial intelligence, both of which are addressed in this collection of exciting new AI theories and experiments. Massively parallel computers have been used to push forward research in traditional AI topics such as vision, search, and speech. More important, these machines allow AI to expand in exciting new ways by taking advantage of research in neuroscience and developing new models and paradigms, among them associate memory, neural networks, genetic algorithms, artificial life, society-of-mind models, and subsumption...

Modification proposed for SRK equation of state  — Oil & Gas Journal
Osman, EA, and Al-Marhoun, MA, "Artificial neural networks models for predicting PVT properties of oil field brines," proceedings, 14th SPE Middle East Oil and Gas Show and Conference, Mar. 12-15, 2005, Manama, Bahrain. 5. Sunday, OO, Ali, S., …

Optimi prototype effectively predicts people at risk of depression  — News-Medical.net
The Optimi prototype is based on artificial neural networks, capable of predicting if a person is at risk of becoming depressed with a reliability of around 85% in the subjects studied. The initial hypothesis states that the central problem and …

Wiley Human Memory Modeled with Standard Analog and Digital Circuits: Inspiration for Man-made Computers
Book (Wiley)
Artificial Intelligence Lecture No. 18
Artificial Intelligence Lecture No. 18
Storing two 2D memories in a neural network using Nengo
Storing two 2D memories in a neural network using Nengo
Guppies - Evolving neural networks (wip) part - Long-Short Term Memory
Guppies - Evolving neural networks (wip) part III - Long-Short Term Memory
Springer Emergent Neural Computational Architectures Based on Neuroscience: Towards Neuroscience-Inspired Computing (Lecture Notes in Computer Science / Lecture Notes in Artificial Intelligence)
Book (Springer)
Springer Computational Neuroscience: Cortical Dynamics: 8th International Summer School on Neural Nets, Erice, Italy, October 31 - November 6, 2003 Revised Lectures (Lecture Notes in Computer Science)
eBooks (Springer)
Springer Artificial Mind System: Kernel Memory Approach (Studies in Computational Intelligence)
Book (Springer)

Related posts:

  1. Artificial neural networks structure
  2. Artificial Neural Networks Brain
  3. Artificial Neural Networks Seminar
  4. Artificial Neural Networks History
  5. Artificial Neural Networks YouTube