Modified AlexNet with CNN Visualisation

This model was used to understand cognitive processing of predicting other individuals goals from various sources of information, like gaze, hand preshape or arm trajectory.

Model Details

Model Description

The model uses AlexNet and changes to the FCC allow for CNN visualisation of the predictions confidence regions.

Developed by: Michael Peres
Model type: AlexNet with adapted for CNN Visualations.
Finetuned from model [optional]: AlexNet

Model Sources

Paper: Ambrosini E, Pezzulo G, Costantini M. The eye in hand: predicting others' behavior by integrating multiple sources of information. J Neurophysiol. 2015 Apr 1;113(7):2271-9. doi: 10.1152/jn.00464.2014. Epub 2015 Jan 7. PMID: 25568158; PMCID: PMC4416586.
Demo: https://youtu.be/XV4zjh63Yfk

Bias, Risks, and Limitations

Model may have learnt specific constants from background to make predictions and not learnt say eye gaze, hand preshape or arm trajectory.

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: RTX 3070Ti
Hours used: 2

Model Card Contact

Michael Peres michaelperes562@gmail.com