Ibragimov, S., Jentzen, A., & Riekert, A. (2022). Convergence to good non-optimal critical points in the training of neural networks: Gradient descent optimization with one random initialization overcomes all bad non-global local minima with high probability.
Style de citation Chicago (17e éd.)Ibragimov, Shokhrukh, Arnulf Jentzen, et Adrian Riekert. Convergence to Good Non-optimal Critical Points in the Training of Neural Networks: Gradient Descent Optimization with One Random Initialization Overcomes All Bad Non-global Local Minima with High Probability. 2022.
Style de citation MLA (9e éd.)Ibragimov, Shokhrukh, et al. Convergence to Good Non-optimal Critical Points in the Training of Neural Networks: Gradient Descent Optimization with One Random Initialization Overcomes All Bad Non-global Local Minima with High Probability. 2022.