PathNet: Evolution Channels Gradient Descent in Super Neural Networks · HackerPapers discussions

PathNet: Evolution Channels Gradient Descent in Super Neural Networks — mentioned by tjwhitaker

Mon, 29 Jun 2020 14:05:02 GMT

I think this is a really interesting area of machine learning. Some efforts have been made in ideas that are tangential to this one. Lots of papers in neuroevolution deal with evolving topologies. NEAT is probably the prime example http://nn.cs.utexas.edu/downloads/papers/stanley.ec02.pdf and another paper I read recently called pathnet that is different but very interesting https://arxiv.org/abs/1701.08734.

Paper and discussion history. A mention is not an endorsement.

PathNet: Evolution Channels Gradient Descent in Super Neural Networks — mentioned by AndrewKemendo

Tue, 28 Mar 2017 06:05:58 GMT

I think this claim would be more credible if there were the any other characteristics of a religion present. Namely: Doctrine, rituals, totems, prayer, and above all it would require that there is some credulity to a higher power/state such as heaven/nirvana that will never be seen by humans. I'd be interested to see some of those as I haven't yet and I've been in the community for a while. What I will grant is that, there are those who speak in the same structure as religious people. "In the future there will be no poverty because machines will make everything we need for free" sounds a…

Paper and discussion history. A mention is not an endorsement.

PathNet: Evolution Channels Gradient Descent in Super Neural Networks — mentioned by T-A

Mon, 20 Mar 2017 11:37:12 GMT

Maybe of interest: https://arxiv.org/abs/1701.08734 https://arxiv.org/abs/1703.00837

Paper and discussion history. A mention is not an endorsement.

PathNet: Evolution Channels Gradient Descent in Super Neural Networks — HN submission

Thu, 09 Mar 2017 17:36:26 GMT

DeepMind's PathNet – potentially describing how general AI will look like

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

PathNet: Evolution Channels Gradient Descent in Super Neural Networks — mentioned by pizza

Thu, 09 Mar 2017 12:19:05 GMT

the paper itself https://arxiv.org/pdf/1701.08734.pdf

Paper and discussion history. A mention is not an endorsement.

PathNet: Evolution Channels Gradient Descent in Super Neural Networks — HN submission

Sat, 18 Feb 2017 18:18:25 GMT

PathNet: Evolution Channels Gradient Descent in Super Neural Networks

60 points; 6 discussion replies on HN. Paper and source history. A submission is not an endorsement.

PathNet: Evolution Channels Gradient Descent in Super Neural Networks — mentioned by brudgers

Sat, 18 Feb 2017 15:04:38 GMT

PathNet paper: https://arxiv.org/abs/1701.08734 For artificial general intelligence (AGI) it would be efficient if multiple users trained the same giant neural network, permitting parameter reuse, without catastrophic forgetting. PathNet is a first step in this direction. It is a neural network algorithm that uses agents embedded in the neural network whose task is to discover which parts of the network to re-use for new tasks. Agents are pathways (views) through the network which determine the subset of parameters that are used and updated by the forwards and backwards passes of the…

Paper and discussion history. A mention is not an endorsement.

PathNet: Evolution Channels Gradient Descent in Super Neural Networks — HN submission

Mon, 13 Feb 2017 16:54:14 GMT

PathNet: Evolution Channels Gradient Descent in Super Neural Networks

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.