Sara Beery
Professor · MIT
Sara Beery is an Assistant Professor at MIT who develops computer vision and machine learning methods for wildlife monitoring and conservation.
- lectures
- 8
- series
- 1
- hours
- 10
Start here
Series and courses
In these lectures
- Gradient descent finds parameters by moving iteratively in the direction of maximal slope on a loss landscape.How to Train a Neural Net
- Deep learning relies on two foundational components: neural networks (stacked linear transformations interleaved with pointwise nonlinearities) and differentiable programming (gradient-based optimization).Introduction to Deep Learning
- A good representation should be compact, explanatory, well-concentrated for similar items, well-separated for different classes, and robust to irrelevant perturbations.Representation Learning: Similarity-Based
Draws on
People cited in the lectures, at the moment of the citation.
- Yann LeCunCited for his tweet about deep learning being superseded by differentiable programming.
- Thomas G. DietterichCited for his tweet defining deep learning as a new style of differentiable programming.
- Jitendra MalikCited for research on long-term context in video action recognition.
- Hongzhou LinProvided image illustration for adversarial perturbations.
- Aleksander MadryProvided illustration on predictive features.
- Andrew NgCited for his famous lecture series on deep learning.
Playlists
1About
Sara Beery is an Assistant Professor at MIT who develops computer vision and machine learning methods for wildlife monitoring and conservation. Her graduate lectures in MIT 6.7960 Deep Learning derive backpropagation and cover recurrent networks, contrastive learning and domain adaptation.
Taught with
Same subject, AI & Machine Learning
Connections
15Their places, courses, books and lectures.




