
5月4日
研討會, 演講, 講座
Department of Mathematics - PhD Student Seminar - Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks
Pruning is a model compression method that removes redundant parameters and accelerates the inference speed of deep neural networks while maintaining accuracy. Most available pruning methods impose various conditions on parameters or features directly.

5月4日
研討會, 演講, 講座
Department of Mathematics - PhD Student Seminar - A Moving Mesh Finite Element Method for Topology Optimization
Many partial differential equations may have solutions with nearly singular behaviors, such as shock waves and boundary layers.

5月4日
研討會, 演講, 講座
Department of Mathematics - PhD Student Seminar - Highest weight crystals for Schur Q-functions
In 1990s, Kashiwara and Lusztig defined crystals as abstraction of crystal bases of quantum group representations.

5月3日
研討會, 演講, 講座
Department of Mathematics - PhD Student Seminar - Apply threshold dynamics algorithm to minimal compliance problem in topology optimization
Inspired by the simple two-step threshold dynamics algorithm which iteratively does convolution and thresholding to simulate the motion of grain boundaries, we developed an algorithm to approach the minimal compliance problem in topology optimization with

5月2日
研討會, 演講, 講座
Department of Mathematics - PhD Student Seminar - Data Adaptive Early Stopping in Split LBI: towards Controlling the False Discovery Rate
Early stopping is a widely-used regularization technique to avoid overfitting in iterative algorithms.

5月2日
研討會, 演講, 講座
Department of Mathematics - PhD Student Seminar - SDE-based deep generative model
Deep generative models are a category of machine learning models that utilizes deep neural networks to model data distributions and generate new samples.

5月2日
研討會, 演講, 講座
Department of Mathematics - PhD Student Seminar - Application of Reinforcement Learning to High-frequency Market Making Strategy
With the increasing usage of the electronic limit order book (LOB) in modern financial markets, high-frequency algorithmic trading has captured over 70 percent of the whole trading volume in various financial markets.

4月29日
研討會, 演講, 講座
Department of Mathematics - Seminar on PDE - Anisotropic Dynamical Horizons Arising in Gravitational Collapse
Black holes are predicted by Einstein's theory of general relativity, and now we have ample observational evidence for their existence.
瀏覽理學院過往舉辦的活動。