Backpropagation (BP) is the most successful and widely used algorithm in deep learning.
However, the computations required by BP are challenging to reconcile with known …

An important difference between brains and deep neural networks is the way they learn.
Nervous systems learn online where a stream of noisy data points are presented in a non-…

Many investors that adopt minimum volatility strategies are inadvertently allowing unnecessary
volatility in their minimum volatility allocations by ignoring the underlying currency …

Approaches to quantitative equity investing have evolved markedly. Thirty years ago, the
focus was on alpha generation, but with the recent decade’s acceptance of smart (alternative) …

The standard way of measuring performance in deep learning is through a test loss: a neural
network is trained to perform some task, and the goal is to get the network to reduce the …

The standard way of measuring performance in deep learning is through a test loss: a neural
network is trained to perform some task, and the goal is to get the network to reduce the …

Predictive coding (PC), a popular neural network model used in neuroscience, has recently
caught the attention of the machine learning community. A flurry of recent work has shown …

Practical Applications Summary In Not All Factor Exposures Are Created Equal , from the 2018
Quantitative Special Issue of The Journal of Portfolio Management, authors Eric Sorensen…

We cross-correlate maps of the thermal Sunyaev–Zeldovich (tSZ) Compton-y parameter
published by Planck with the projected distribution of galaxies in a set of low-redshift …

Predictive coding (PC) is a general theory of cortical function. The local, gradient-based
learning rules found in one kind of PC model have been shown to closely approximate back-…