Statistical Mechanics of Deep Learning

N/A

# link_1cscju1v23r.pdf ## Metadata - PDFFormatVersion=1.4 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Keywords=neural networks,machine learning,dynamical phase transitions,chaos,spin glasses,jamming,random matrix theory,interacting particle systems,nonequilibrium statistical mechanics - ModDate=D:20200623112945-07'00' - CreationDate=D:20200623112945-07'00' - Producer=iText 4.2.0 by 1T3XT - Subject=Annu. Rev. Condens. Matter Phys. 2020.11:501-528 - Author=Yasaman Bahri, Jonathan Kadmon, Jeffrey Pennington, Sam S.

saved by

• Divit Rawal
• David Jihoon Kim

related reading

• [2304.03408] Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networksarxiv.org
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• [2205.09653] Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networksarxiv.org
• A Theory of Deep Learning | Elements of a Vector Spaceelonlit.com
• nn-notes.pdfboris-hanin.github.io
• Neural networks: from the perceptron to deep netsarxiv.org
• The Little Book of Deep Learningfleuret.org
• Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
• Understanding deep learning requires rethinking generalizationarxiv.org
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• Neural network training makes beautiful fractals | Jascha’s blogsohl-dickstein.github.io
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org