Learning Theory of Deep Structured Neural Networks

Mathematics

1. Neural Network 100%
2. Deep Neural Network 48%
3. Deep Learning Method 37%
4. Convolutional Neural Network 37%
5. Regression Function 33%
6. Approximation Theory 25%
7. Partial Differential Equation 25%
8. Linear Constraint 22%
9. Functionals 22%
10. Residuals 22%
11. Lagrangian 22%
12. Alternating Direction Method of Multipliers 22%
13. Saddle Point 22%
14. Quantile 22%
15. Convolutional Layer 22%
16. Network Model 22%
17. Connected Layer 22%
18. Regularization 22%
19. Approximation Error 22%
20. Moreau Envelope 22%
21. Radial Function 22%
22. Function Value 22%
23. Least Square 22%
24. Structural Parameter 22%
25. Optimal Control Problem 22%
26. Error Bound 18%
27. Stochastics 16%
28. Approximates 16%
29. Loss Function 16%
30. Kriging 16%
31. Energy Function 16%
32. Integral Operator 11%
33. Point Estimation 11%
34. Total Number 11%
35. Continuous Functionals 11%
36. Space of Analytic Functions 11%
37. Hilbert Space 11%
38. Polynomial Feature 11%
39. Wide Range 11%
40. Local Minimizer 11%
41. Hlder Space 11%
42. Downsampling Operator 11%
43. Unit Ball 11%
44. Polynomial 11%
45. Transition State 11%
46. Exp 11%
47. Superiority 11%
48. Windowing Function 11%
49. Probability Measure 11%
50. Ridge Regression 11%
51. Empirical Risk Minimization 11%
52. Univariate Function 11%
53. Good Approximation 7%
54. Output Function 7%
55. Step Size 7%
56. Connected Network 7%
57. Multivariate Approximation 7%
58. Hypothesis Space 7%
59. Wavelet Analysis 7%
60. Batch Learning 7%
61. Mathematical Analysis 7%
62. Wavelet 7%
63. Hamilton-Jacobi Equation 7%
64. Iterative Scheme 7%
65. Characteristic Curve 7%
66. Training Sample 6%
67. Grand Challenge 5%
68. Learning Task 5%
69. Variance 5%
70. Gradient Vector 5%
71. Ritz Method 5%
72. Solving Differential Equation 5%
73. Hessian Matrix 5%
74. Dimensional Space 5%
75. Higher Dimensions 5%
76. Total Variation 5%
77. Optimal Criterion 5%
78. Experimental Design 5%