Tim Räz
Biographic Data
| ID | 1045425 |
|---|---|
| NAME | Tim Räz |
| GIVEN NAMES | Tim |
| FAMILY NAME | Räz |
| SIGNATURE | RÄZ T |
| AFFILIATIONS | University of Bern |
| ORCID | 0000-0002-8464-4190 |
| VERIFIED | Yes |
| TOTAL WORKS | 8 |
| TOTAL CITATIONS | 18 |
| WORKS AS AUTHOR | 8 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2015 |
| LATEST PUBLICATION YEAR | 2024 |
| H-INDEX | 4 |
The Importance of Understanding Deep Learning
Some machine learning models, in particular deep neural networks (DNNs), are not very well understood; nevertheless, they are frequently used in science. Does this lack of understanding pose a problem for using DNNs to understand empirical phenomena? Emily Sullivan has recently argued that understanding with DNNs is not limited by our lack of understanding of DNNs themselves. In the present paper, we will argue, contra Sullivan, that our current …
ML interpretability
The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI that aim to make these models more transparent. The goal of this paper is to clarify the nature of interpretability by focussing on the other end of the "interpretability spectrum". The reasons why some models, l…
Understanding Deep Learning with Statistical Relevance
This paper argues that a notion of statistical explanation, based on Salmon’s statistical relevance model, can help us better understand deep neural networks. It is proved that homogeneous partitions, the core notion of Salmon’s model, are equivalent to minimal sufficient statistics, an important notion from statistical inference. This establishes a link to deep neural networks via the so-called Information Bottleneck method, an information-theor…
Philosophy of science at sea
In computer science, there are efforts to make machine learning more interpretable or explainable, and thus to better understand the underlying models, algorithms, and their behavior. But what exactly is interpretability, and how can it be achieved? Such questions lead into philosophical waters because their answers depend on what explanation and understanding are-and thus on issues that have been central to the philosophy of science. In this pap…
Understanding climate change with statistical downscaling and machine learning
The silent hexagon
The Volterra Principle Generalized
Michael Weisberg and Kenneth Reisman argue that the Volterra Principle can be derived from multiple predator-prey models and that, therefore, the Volterra Principle is a prime example for robustness analysis. In the current article, I give new results regarding the Volterra Principle, extending Weisberg’s and Reisman’s work, and I discuss the consequences of these results for robustness analysis. I argue that we do not end up with multiple, indep…
Outline of a dynamical inferential conception of the application of mathematics
Understanding Deep Learning with Statistical Relevance
This paper argues that a notion of statistical explanation, based on Salmon’s statistical relevance model, can help us better understand deep neural networks. It is proved that homogeneous partitions, the core notion of Salmon’s model, are equivalent to minimal sufficient statistics, an important notion from statistical inference. This establishes a link to deep neural networks via the so-called Information Bottleneck method, an information-theor…
Philosophy of science at sea
In computer science, there are efforts to make machine learning more interpretable or explainable, and thus to better understand the underlying models, algorithms, and their behavior. But what exactly is interpretability, and how can it be achieved? Such questions lead into philosophical waters because their answers depend on what explanation and understanding are-and thus on issues that have been central to the philosophy of science. In this pap…
Understanding climate change with statistical downscaling and machine learning
The Volterra Principle Generalized
Michael Weisberg and Kenneth Reisman argue that the Volterra Principle can be derived from multiple predator-prey models and that, therefore, the Volterra Principle is a prime example for robustness analysis. In the current article, I give new results regarding the Volterra Principle, extending Weisberg’s and Reisman’s work, and I discuss the consequences of these results for robustness analysis. I argue that we do not end up with multiple, indep…
The silent hexagon
Outline of a dynamical inferential conception of the application of mathematics
The silent hexagon
The Volterra Principle Generalized
Michael Weisberg and Kenneth Reisman argue that the Volterra Principle can be derived from multiple predator-prey models and that, therefore, the Volterra Principle is a prime example for robustness analysis. In the current article, I give new results regarding the Volterra Principle, extending Weisberg’s and Reisman’s work, and I discuss the consequences of these results for robustness analysis. I argue that we do not end up with multiple, indep…
Understanding climate change with statistical downscaling and machine learning
Understanding Deep Learning with Statistical Relevance
This paper argues that a notion of statistical explanation, based on Salmon’s statistical relevance model, can help us better understand deep neural networks. It is proved that homogeneous partitions, the core notion of Salmon’s model, are equivalent to minimal sufficient statistics, an important notion from statistical inference. This establishes a link to deep neural networks via the so-called Information Bottleneck method, an information-theor…
Philosophy of science at sea
In computer science, there are efforts to make machine learning more interpretable or explainable, and thus to better understand the underlying models, algorithms, and their behavior. But what exactly is interpretability, and how can it be achieved? Such questions lead into philosophical waters because their answers depend on what explanation and understanding are-and thus on issues that have been central to the philosophy of science. In this pap…
The Importance of Understanding Deep Learning
Some machine learning models, in particular deep neural networks (DNNs), are not very well understood; nevertheless, they are frequently used in science. Does this lack of understanding pose a problem for using DNNs to understand empirical phenomena? Emily Sullivan has recently argued that understanding with DNNs is not limited by our lack of understanding of DNNs themselves. In the present paper, we will argue, contra Sullivan, that our current …
ML interpretability
The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI that aim to make these models more transparent. The goal of this paper is to clarify the nature of interpretability by focussing on the other end of the "interpretability spectrum". The reasons why some models, l…
Computer Science (7 works) · Epistemology (6 works) · Artificial Intelligence (5 works) · Mathematics (5 works) · Explainable Artificial Intelligence (XAI (4 works) · Machine learning (4 works) · Philosophy (4 works) · Adversarial Robustness in Machine Learning (3 works) · Philosophy and History of Science (3 works) · Artificial Intelligence (2 works)