NIP Class Papers, Assignment 2
Deadline 6. April 2018, 4pm
Pick one of the papers from the list below. Do not pick the paper we discussed in class (Kirpatrick et al.).
- Describe the central problem the paper is attempting to address.
- How does it build on previous work and evidence?
- Briefly describe the methods used, focussing on aspects central to the results.
- Summarise the key finding(s) and advances presented in the paper.
- Discuss the biological plausibility if you have chosen a paper about artificial systems, or the insights that could benefit artificial systems if you have chosen a biological paper.
Each question has equal weight in the final mark. There is no word limit or minimum length length we expect, but please ensure you provide sufficient information to address each question and demonstrate understanding. As a rough guide, if your answer
to a question has less than 150 words, check if your answer is sufficiently informative.
Use the DICE submit command, in case this fails, you can hand in a hardcopy at the ITO. Command: submit nip cw2 file.pdf
Yamins et al, Performance-optimized hierarchical models predict neural responses in higher visual cortex
Neural inspired parallel hardware. Furber et al. (2014)
Spike based visual computation. Perez-Carrasco et al (2013)
Linking ML networks to neural data from monkey area IT. Yamins et al.(2014)
Sampling with neurons. Buesing et al.(2011)
Autoencoders. Hinton et al (2006)
Large scale unsupervised learning
Le et al (2012)
Spontaneous cortical activity reveals hallmarks of an optimal internal
model of the environment. Berkes et al. (2011)
Visual stimuli recruit intrinsically generated cortical ensembles. Miller et al. (2014)
Learning with hierarchical-deep models. Salakhutdinov et al. (2013)
Spiking Boltzmann machines. Hinton and Brown (2000)
Deep Learning Models of the Retinal Response to Natural Scenes. McIntosh et al. (2016).
This paper will be discussed in class, do not write aboit it: Overcoming catastrophic forgetting in neural networks. Kirkpatrick et al. (2017)
|Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail:
Please contact our webadmin with
any comments or corrections. Logging and Cookies
Unless explicitly stated otherwise, all material is copyright ©
The University of Edinburgh