Thread by @ArsalaanAli6, DeepMind & UCL Lecture series on Deep Learning (DL) DL: ability to [...]

DeepMind & UCL Lecture series on Deep Learning (DL)

DL: ability to extract useful patterns from data

Discuss AlphaGo, AlphaZero & AlphaFold (predicts 3D structure of protein from amino acid sequence)

Limitations: data efficiency and energy consumption

Wojciech Czarnecki goes through the foundations of Neural Networks

Neural networks are a series of algorithms mimicking the operations of a human brain to recognise relationships between vast amounts of data.

"Modern GPUs enabled the one-layer networks of the 60s & 2-3 layer nets of the 80s to blossom into the 50 layer nets today. “Deep learning” is the depth of the network’s layers. Currently, DL is responsible for the best-performing systems in AI research" https://news.mit.edu/2017/explained-neural-networks-deep-learning-0414

Explained: Neural networks

“Deep learning,” the machine-learning technique behind the best-performing artificial-intelligence systems of the past decade, is really a revival of the 70-year-old concept of neural networks.

https://news.mit.edu/2017/explained-neural-networks-deep-learning-0414

You can follow @ArsalaanAli6.

Tip: mention @twtextapp on a Twitter thread with the keyword “unroll” to get a link to it.

Latest Threads Unrolled: