CogSci Seminar Fall 2018

These are up (as off last week). Please respond to this post with your comments :)

There is no class 11/21 because of the Thanksgiving holiday, see the University calendar . Feel free to reach out if you have any questions/concerns about your paper/project. I will be in town and on email :)

Readings are up! We have an external speaker next week, Burt Monroe. I distributed a Doodle poll for people to sign up to meet with him; please let me know if you didn't get it (which means you're not on the IIS mailing list).

Readings are up for next week 😀 In addition to the speaker's reading I've assigned some background reading on SVD and latent semantic analysis/indexing. These are closely related to PCA and are a kind of unsupervised learning.

Readings are up for next week 😀 Please also take a look at the data description for the latest Kaggle lab (link distributed yesterday). The lab for next week will step through the Zuur protocol to build a predictive model for this dataset.

Readings are up in the normal place. This week's readings are fairly deep into neural networks, which we haven't really talked about. Rather than give you something else to read, I'm going to try to give you what you need to know in this post. First, there are two kinds of neural networks, those that have recurrent connections and those that don't. A recurrent connection is something like this: The circle represents a neuron (AKA node; unit) and the arrow represents a connection from the neuron back to itself. Recurrent connections can also be more distant, e.g. from a child neuron to its parent, as long as there is a path that leads back to the originating neuron, e.g. child --> parent --> child. The important thing to understand about recurrent neural networks is that they are dynamical systems that unfold in time. Imagine that we initialize the neuron above to have a value (AKA energy; activation) of 1 and the recurrent connection to have a streng