Join our community for ML news, talks and tutorials: feather-ai.com/discord
Joined January 2021
- Tweets 69
- Following 170
- Followers 221
- Likes 35
30 Photos and videos
13 Oct 2021
Tired of spending time and money on copywriting and editing images?
feather-ai.com/marketing
5
4 Oct 2021
Positional Encoding allows us to inject information about the order of the sequence into an otherwise position-indifferent architecture. The original Transformer does this by injecting sinusoids into the word embeddings.
youtu.be/LSCsfeEELso
#ArtificialIntelligence
Info:👇
1
2
2
27 Sep 2021
In this Transformers from scratch episode, we look at how we can build and code up the Encoder Layer in its entirety:
youtu.be/z5eymymeMnU
#ArtificialIntelligence #NLProc #MachineLearning #DataScience
1
1
2
26 Sep 2021
Transformers: Residual Connections, Layer Normalization, and Position Wise Feedforward Networks
In this episode, we take a look the components shared across all transformer sublayers
youtu.be/Wc8qJxoD52g
#ArtificialIntelligence #nlproc
2
23 Sep 2021
Transformers: Multi-head attention
In this episode/lesson, we look at upping the self-attention mechanism we looked at previously to the multi-head variant. Includes the theory and code.
youtu.be/Y4qft_HoPUw
#NLProc #ArtificialIntelligence #MachineLearning #DataScience
1
2
feather retweeted
22 Sep 2021
Transformers: Self-attention
In this video tutorial series, we take a look at the heart of the Transformer, the self-attention mechanism. After an intuitive breakdown of how it works, we code up the mechanism.
youtu.be/1BFE1Tfs8tM
#NLProc #ArtificialIntelligence #ML #Data
1
2
4
22 Sep 2021
Transformers: Self-attention
In this video tutorial series, we take a look at the heart of the Transformer, the self-attention mechanism. After an intuitive breakdown of how it works, we code up the mechanism.
youtu.be/1BFE1Tfs8tM
#NLProc #ArtificialIntelligence #ML #Data
1
2
4
