Marc Mézard: "Machine learning with neural networks: the importance of data structure"
11 Dec 2019
48m
Institute for Pure & Applied Mathematics (IPAM) · Science
Institute for Pure & Applied Mathematics (IPAM)
The Institute for Pure and Applied Mathematics (IPAM) is a National Science Foundation Math Institute at the University of California, Los Angeles (UCLA) that fosters the interaction of mathematics with a broad range of science and technology, builds new interdisciplinary research communities, promotes mathematical innovation, and engages and transforms the world through mathematics. IPAM fulfills its mission through workshops and programs that connect mathematics and other disciplines or multiple areas of mathematics. These activities bring in thousands of visitors annually from academia, government, and industry. The NSF has encouraged IPAM to make the scientific presentations of our speakers available to a wider audience. While this YouTube channel contains many of our most popular videos, our full video archive is available at www.ipam.ucla.edu/videos.
Episodes
Maxwell Hutchinson: "Boltzmann Trees: a physically inspired randomization for robust modeling of..."
11 Dec 2019
48m
Maria Schuld: "Innovating machine learning with near-term quantum computing"
11 Dec 2019
44m
Carlo Baldassi: "On the existence of wide flat minima in neural network landscapes: analytic and..."
11 Dec 2019
50m
Daniel Roberts: "Deep learning as a toy model of the 1/N-expansion and renormalization"
11 Dec 2019
1h 3m
Riccardo Zecchina: "Evidence for local entropy optimization in machine learning, physics and neu..."
11 Dec 2019
58m
Haim Sompolinsky: "Statistical Mechanics of Deep Manifolds: Mean Field Geometry in High Dimension"
11 Dec 2019
1h 3m
Masayuki Ohzeki: "Quantum annealing and machine learning - new directions of quantum"
10 Dec 2019
58m
Chiara Cammarota: "High-dimensional cost landscape and gradient descent in Tensor PCA and its ge..."
10 Dec 2019
53m
Gérard Ben Arous: "Which is worse: a weak signal lost in entropy or trapping by topological comp..."
10 Dec 2019
48m
Yann LeCun: "Energy-Based Self-Supervised Learning"
10 Dec 2019
1h 0m
Michele Ceriotti: "Machine learning for atomic and molecular simulations"
10 Dec 2019
53m
Risi Kondor: "Fourier space neural networks"
10 Dec 2019
53m
Eric Vanden-Eijnden: "Trainability and accuracy of artificial neural networks"
10 Dec 2019
56m
Rémi Monasson: "Capacity-resolution trade-off in the optimal learning of multiple low-dimensiona..."
10 Dec 2019
36m
Lenka Zdeborová: "Understanding machine learning via exactly solvable statistical physics models"
10 Dec 2019
52m
Lukáš Pospíšil: "Towards a low-cost scalable data-driven modeling of coupled systems and non-sta..."
13 Nov 2019
36m
Joan Bruna: "Geometric Insights for Nonlinear TD Convergence"
12 Nov 2019
39m
Stefan Klus: "Data-driven transfer operator approximation, model reduction, and system identific..."
12 Nov 2019
41m
Bing Brunton: "Fields and flows in neural dynamics"
12 Nov 2019
52m
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.