Frontiers of Engineering Reports on Leading-Edge Engineering from the 2017 Symposium (2018) / Chapter Skim
Currently Skimming:
The Roles of Machine Learning in Biomedical Science - Konrad Paul Kording, Ari S. Benjamin, Roozbeh Farhoodi, and Joshua I. Glaser
The Roles of Machine Learning in Biomedical Science - Konrad Paul Kording, Ari S. Benjamin, Roozbeh Farhoodi, and Joshua I. Glaser
Pages 61-72
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 61... ...
Glaser Northwestern University While the direct goal of biological modeling is to describe data, it ultimately aims to find ways of fixing systems and enhancing understanding of system objectives, algorithms, and mechanisms. Thanks to engineering applications, machine learning is making it possible to model data extremely well, without using strong assumptions about the modeled system.
|
From page 62... ...
The field of machine learning is undergoing a revolution. It has moved from a niche discipline to a major driver of economic activity over the past couple of decades as progress revolutionizes web searching, speech to text, and countless other areas of economic importance.
|
From page 63... ...
were collected from Google Patents using the same keywords. USES OF MACHINE LEARNING FOR BIOMEDICAL RESEARCH Many kinds of questions can be answered using machine learning techniques.
|
From page 64... ...
If a human-generated model produces results that are very different from the ML benchmark, it may be because important principles are missing or because the modeling is misguided. If, on the other hand, a model based on human intuition is very close to the ML benchmark, it is more likely that the posited concepts are, indeed, meaningful.
|
From page 65... ...
. It is unclear how far the typical approach in biomedical research, drawing on concepts of necessity and sufficiency, can help to enhance understanding of the bulk of activity in complex interacting systems (Gomez-Marin 2017)
|
From page 66... ...
For example, Lamarckian evolution explains a lot of data about species, but it was based on a fundamentally misleading concept of causal transmission of traits. The problem of apparent fit affects human intuition–based models, but not ML models, which, by design, do not produce a meaningful causal interpretation.
|
From page 67... ...
To analyze the advantages of using standard machine learning, we implemented many approaches: the linear Wiener filter, the nonlinear extension called the Wiener cascade, the Kalman filter, nonlinear support vector machines, extreme gradient–boosted trees, and various neural networks (Figure 2)
|
From page 68... ...
SVR Feedfrwrd NN GRU Ensemble 1.0 Motor Cortex 0.2 Motor Cortex pseudo R2 R2 0.1 0.6 0 WF WC KF SVR XGB FNN RNN GRU LSTM Ens GLM FNN XGB Ens 1.0 Somatosensory Cortex 0.2 Somatosensory Cortex pseudo R2 0.1 R2 0.6 0 WF WC KF SVR XGB FNN RNN GRU LSTM Ens GLM FNN XGB Ens 0.75 Hippocampus 0.2 Hippocampus pseudo R2 0.1 R2 0.25 0 WF WC KF SVR XGB FNN RNN GRU LSTM Ens GLM FNN XGB Ens FIGURE 2 State-of-the-art machine learning decoding (left) and encoding (right)
|
From page 69... ...
It can be difficult to guess features that relate to neural activity in exactly the form specified by the GLM. Interestingly, despite the fact that the space was rather low dimensional, GLMs performed poorly relative to modern machine learning.
|
From page 70... ...
2017. Modern machine learning far outperforms GLMS at predicting spikes.
|
From page 71... ...
2012. What the no free lunch theorems really mean: How to improve search algorithms.
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.