Our favorite open ML courses!

Topics?

1. Deep Learning by @ylecun
2. NLP with Deep Learning by @stanfordnlp
3. Deep Learning for NLP by @CompSciOxford and @DeepMind

Here they are⬇️

@ylecun

1) Deep Learning by @ylecun

This unique course material consists of:
- close captioned lecture videos
- detailed written overviews
- executable Jupyter Notebooks with PyTorch implementations

https://twitter.com/TheSequenceAI/status/1358071702912172034

@stanfordnlp

2) NLP with Deep Learning by @stanfordnlp

Course from one of the famous NLP Groups in the world.

https://twitter.com/TheSequenceAI/status/1438509477167345664

Read 4 tweets

TheSequence

@TheSequenceAI

20 Sep

AutoML means using ML to create better ML models.

Meta-learning improves the learning of sophisticated tasks by reusing knowledge.

3 main forms of meta-learning relevant to AutoML⬇️

1) Based on Model Evaluations

Learn new tasks based on the configuration of models based on similar tasks.

Configuration = hyperparameter settings, pipeline, and/or network architecture components.

2) Based on Task Properties

Transfer knowledge between empirically similar tasks.

This method describes tasks as a set of meta-features and predicts the outcome of similar tasks by evaluating the distance with its meta-feature vector and other tasks.

Read 4 tweets

TheSequence

@TheSequenceAI

14 Sep

Master Neural Architecture Search (NAS) to automate the creation of neural networks.

4 topics you need to cover⬇️

@IBMResearch

1) The concept of NAS

1. Read one of the fundamental papers, "A Survey on Neural Architecture Search" @IBMResearch
2. Explore our dedicated Edge#4 for free thesequence.substack.com/p/thesequence-…

2) NAS algorithms

1. Differentiable Architecture Search
2. Differentiable ArchiTecture Approximation
3. eXperts Neural Architecture Search
4. Petridish (Read "Efficient Forward Architecture Search")

Read 5 tweets

TheSequence

@TheSequenceAI

4 Sep

NAS is one of the most promising areas of deep learning.

But it remains super difficult to use.

Archai = an open-source framework that enables the execution of state-of-the-art NAS methods in PyTorch.⬇️

Archai enables the execution of modern NAS methods from a simple command-line interface.

Archai developers are striving to rapidly update the list of algorithms.

Current deck:
- PC-DARTS
- Geometric NAS
- ProxyLess NAS
- SNAS
- DATA
- RandNAS
2/5

Benefits for the adopters of NAS techniques:
- Declarative Approach and Reproducibility
- Search-Space Abstractions
- Mix-and-Match Techniques
- & more!

You can find more details here: microsoft.github.io/archai/feature…
3/5

Read 5 tweets

Share this page!

TheSequence

Try unrolling a thread yourself!

More from @TheSequenceAI

TheSequence

TheSequence

TheSequence

TheSequence

TheSequence

TheSequence

Did Thread Reader help you today?

Like this author's thread?