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
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.
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