Video Lectures

In computer vision, generalization of neural representations is usually measured on i.i.d. data. This hides the fact that representations often struggle to generalize to non-i.i.d data and fail to overcome the biases inherent in visual datasets. I...

Stochastic Gradient Descent (SGD) is the de facto optimization algorithm for training neural networks in modern machine learning, thanks to its unique scalability to problem sizes where the data points, the number of data points, and the number of...

I will discuss partition functions in three-dimensional quantum gravity with negative cosmological constant in canonical quantization. I will review the phase space and its quantization in detail, which leads to the computation of the gravity...

Recent deep learning models have achieved impressive predictive performance by learning complex functions of many variables, often at the cost of interpretability. This lecture first defines interpretable machine learning in general and introduces...

In computer vision, generalization of neural representations is usually measured on i.i.d. data. This hides the fact that representations often struggle to generalize to non-i.i.d data and fail to overcome the biases inherent in visual datasets. I...