Welcome Survey: COMP 150 BDL

JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.

Welcome Survey: COMP 150 BDL - Fall 2019

Help us get to know you better.

What is the probability you will take this course? (Put 1.0 if certain, 0.0 if auditing) *

Full Name *

Email Address (____@tufts.edu) *

What kind of student are you? *

Ph.D. student, School of Engineering

Masters student, School of Engineering

Undergraduate, School of Engineering

Undergraduate, School of Arts & Sciences

Other Ph.D. student

Other Masters student

Other Undergraduate student

Required

Which Machine Learning courses have you taken before (if any)? *

COMP 135 (Introduction to Machine Learning), or equivalent at other university

COMP 136 (Statistical Pattern Recognition), or equivalent at other university

COMP 150 (Deep Learning for Computer Vision), or equivalent at other university

Other:

Required

Rank your Familiarity with Concepts *

Expert.

Capable.

Tried it before but still learning.

Never tried it but seen it in a course.

Never heard of it.

Bayes Theorem

Bayesian Hierarchical Models (e.g. Gaussian mixtures, Hidden Markov Models)

Basic Unsupervised Learning (k-means, PCA, etc)

Basic Supervised Learning (Linear/Logistic regression, nearest-neighbors)

Kernel Methods (SVMs, kernel trick, Mercer's theorem)

Basic Feedforward Neural Networks (e.g. multi-layer perceptrons)

Gaussian Processes for Regression or Classification

Neural Networks for Images (e.g. Convolutional NNs)

Neural Networks for Text/Sequences (e.g. LSTMs, RNNs, etc)

Bayesian Inference via Markov Chain Monte Carlo

Inference via Expectation-maximization (EM algorithm)

Bayesian Inference via Variational Optimization

Inference via Loss Function Minimization (gradient-descent)

Expert.

Capable.

Tried it before but still learning.

Never tried it but seen it in a course.

Never heard of it.

Bayes Theorem

Bayesian Hierarchical Models (e.g. Gaussian mixtures, Hidden Markov Models)

Basic Unsupervised Learning (k-means, PCA, etc)

Basic Supervised Learning (Linear/Logistic regression, nearest-neighbors)

Kernel Methods (SVMs, kernel trick, Mercer's theorem)

Basic Feedforward Neural Networks (e.g. multi-layer perceptrons)

Gaussian Processes for Regression or Classification

Neural Networks for Images (e.g. Convolutional NNs)

Neural Networks for Text/Sequences (e.g. LSTMs, RNNs, etc)

Bayesian Inference via Markov Chain Monte Carlo

Inference via Expectation-maximization (EM algorithm)

Bayesian Inference via Variational Optimization

Inference via Loss Function Minimization (gradient-descent)

Why are you taking this course? What are you most excited about? *

What questions do you have? What are you concerned about? *

What (if anything) related to BDL would you like to see covered in this course that is not currently on the schedule? *

Submit

Clear form

Never submit passwords through Google Forms.

This form was created inside of Michaelchughes.com. Report Abuse

Forms