Choose Your Weapon: Survival Strategies for Depressed AI Academics · HackerPapers discussions

Choose Your Weapon: Survival Strategies for Depressed AI Academics — mentioned by newsoul

Wed, 24 Jul 2024 05:10:35 GMT

Choose Your Weapon: Survival Strategies for Depressed AI Academics https://arxiv.org/abs/2304.06035

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

Choose Your Weapon: Survival Strategies for Depressed AI Academics — HN submission

Wed, 03 Apr 2024 01:07:34 GMT

Choose your weapon: Survival strategies for depressed AI academics

124 points; 110 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Choose Your Weapon: Survival Strategies for Depressed AI Academics — mentioned by bob1029

Mon, 17 Apr 2023 21:17:21 GMT

I strongly believe the next generation of models will be based upon spiking neural concepts wherein action potentials are lazily-evaluated throughout the network (i.e. event-driven). There are a few neuron models that can be modified (at some expense to fidelity) in order to tolerate arbitrary delays between simulation ticks. Using actual latency between neurons as a means of encoding information seems absolutely essential if we are trying to emulate biology in any meaningful way. Spiking networks also lend themselves nicely to some elegant learning rules, such as STDP. Being able to perform…

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

Choose Your Weapon: Survival Strategies for Depressed AI Academics — mentioned by thangngoc89

Fri, 14 Apr 2023 06:58:51 GMT

I tried to run the automatic_mask_generator notebook [1] but the results is more noisy then the everything mode on the demo website. Are the parameters used in the demo's website published anywhere? [1]: https://arxiv.org/abs/2304.06035

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

Choose Your Weapon: Survival Strategies for Depressed AI Academics — HN submission

Fri, 14 Apr 2023 00:21:41 GMT

Choose Your Weapon: Survival Strategies for Depressed AI Academics

144 points; 190 discussion replies on HN. Paper and source history. A submission is not an endorsement.