Digests » 62
this week's favorite
With the advent of AI assistants, initially developed for structured databases and manually curated knowledge graphs, answers to the types of basic fact-based questions people encounter during the course of regular conversation became keystrokes or a verbal cue away.
We are surprised to find that BERT's peak performance of 77% on the Argument Reasoning Comprehension Task reaches just three points below the average untrained human baseline. However, we show that this result is entirely accounted for by exploitation of spurious statistical cues in the dataset. We analyze the nature of these cues and demonstrate that a range of models all exploit them. This analysis informs the construction of an adversarial dataset on which all models achieve random accuracy. Our adversarial dataset provides a more robust assessment of argument comprehension and should be adopted as the standard in future work.
This paper investigates various machine learning trading and portfolio optimisation models and techniques. The notebooks to this paper are Python based. By last count there are about 15 distinct trading varieties and around 100 trading strategies. Code and data are made available where appropriate. The hope is that this paper will organically grow with future developments in machine learning and data processing techniques. All feedback, contributions and criticisms are highly encouraged.
Scientific computing is increasingly incorporating the advancements in machine learning and the ability to work with large amounts of data. At the same time, machine learning models are becoming increasingly sophisticated and exhibit many features often seen in scientific computing, stressing the capabilities of machine learning frameworks. Just as the disciplines of scientific computing and machine learning have shared common underlying infrastructure in the form of numerical linear algebra, we now have the opportunity to further share new computational infrastructure, and thus ideas, in the form of Differentiable Programming.
Recurrent Neural Networks (RNNs) are a kind of neural network that specialize in processing sequences. They’re often used in Natural Language Processing (NLP) tasks because of their effectiveness in handling text. In this post, we’ll explore what RNNs are, understand how they work, and build a real one from scratch (using only numpy) in Python.