posts – Emilio Cantu-Cervini

TENT: Fully Test-Time Adaptation By Entropy Minimization

An attempted (partial) paper reproduction

deep learning

paper

Once a model is deployed the feature (covariate) data distribution might shift from that seen during training. These shifts make models go out-of-distribution and worsen…

Building a university event embedding recommender

wolverine events

I am currently a grad student at the University of Michigan and like to attend seminars, lectures, and social events when I can. However, I often attend the same weekly…

RNNs from scratch exercises

deep learning

exercises

Where I build up intuition for RNNs and attempt to solve the exercises in section 9.5 of the d2l book from scratch in pytorch (without using the d2l library).

A Closer Look at Memorization in Deep Networks

An attempted (partial) paper reproduction

deep learning

paper

This paper argues that memorization is a behavior exhibited by networks trained on random data, as, in the absence of patterns, they can only rely on remembering examples.…

Approximate Nearest Cosine Neighbors

cs

quick intro

Using Random Hyperplane LSH

Understanding Batch Normalization

An attempted (partial) paper reproduction

deep learning

paper

The paper investigates the cause of batch norm’s benefits experimentally. The authors show that its main benefit is allowing for larger learning rates during training. In…

Batch Norm exercises

deep learning

exercises

Where I attempt to solve the exercises in section 8.5 of the d2l book from scratch in pytorch (without using the d2l library).

LeNet exercises

deep learning

exercises

Where I attempt to solve the exercises in section 7.6 of the d2l book from scratch in pytorch (without using the d2l library).

Deep Learning is Robust to Massive Label Noise

An attempted (partial) paper reproduction

deep learning

paper

The paper shows that neural networks can keep generalizing when large numbers of (non-adversarially) incorrectly labeled examples are added to datasets (MNIST, CIFAR, and…