Scholar
Nal Kalchbrenner
Google Scholar ID: LFyg0tAAAAAJ
Google DeepMind
Citations & Impact
Citations
42,152
H-index
35
i10-index
46
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Proposed some of the first full-sentence neural encoder-decoders with beam search decoding; developed large-scale and scalable autoregressive models for images and videos such as PixelRNN; worked on WaveNet and WaveRNN architectures for high-fidelity voice generation; part of the AlphaGo project that beat top human player Lee Sedol; proposed and helped launch high-accuracy neural weather models based on the MetNet series.
Research Experience
- Worked in deep learning across multiple domains: language modeling and machine translation, image and video modeling, speech and audio generation, search and reinforcement learning in the board game Go, and AI for physical weather.
Education
- Stanford University, Symbolic Systems and Philosophy; University of Amsterdam, Theoretical Computer Science; Oxford University, PhD in Computer Science.
Background
- A researcher and founder in artificial intelligence and deep learning. I have been interested in the notion of 'how one learns' since my early studies. Throughout my early years, I have looked at this problem from a multitude of perspectives, including the philosophical, cognitive, logico-mathematical, neuroscientific, and statistical ones. Eventually, I matured to the concept of a distributed representation as the then most powerful representation for knowledge and learning.
Miscellany
- Born in Lugano, a picturesque Italian-speaking town in southern Switzerland.
Co-authors