I highly recommend listening to the latest eposide of @therobotbrains podcast with @ilyasut.
therobotbrains.ai/podcasts/episoβ¦
Here are some insights I found particulalry interesting π
therobotbrains.ai/podcasts/episoβ¦
Here are some insights I found particulalry interesting π
"Neural networks are parallel computers"
That is why they are so powerful - you can train a generic computer to solve your problem. This is also the driver behind Software 2.0 - neural network are becoming more and more capable of solving all kinds of problems.
That is why they are so powerful - you can train a generic computer to solve your problem. This is also the driver behind Software 2.0 - neural network are becoming more and more capable of solving all kinds of problems.
"Neural networks perform well on tasks that humans can perform very quickly"
Humans don't think much when listening, observing or performing simple tasks.
This means that a neural network can be trained to be good at it as well: NLP, computer vision and reinforcement learning.
Humans don't think much when listening, observing or performing simple tasks.
This means that a neural network can be trained to be good at it as well: NLP, computer vision and reinforcement learning.
"Neural networks are formalized intuition"
Humans and especially experts in some domain are very good at heuristics - they have a gut feeling. Experts playery for exampe can look at a situation and instantly have feeling what is going on.
Same with neural networks.
Humans and especially experts in some domain are very good at heuristics - they have a gut feeling. Experts playery for exampe can look at a situation and instantly have feeling what is going on.
Same with neural networks.
β’ β’ β’
Missing some Tweet in this thread? You can try to
force a refresh
γ
