94 articles

📰 Dev.to · Rijul Rajesh

Articles from Dev.to · Rijul Rajesh · 94 articles · Updated every 3 hours · View all reads

All ⚡ AI Lessons (9061) ArXiv cs.AIDev.to · FORUM WEBForbes InnovationOpenAI NewsDev.to AIHugging Face Blog
Understanding Transformers Part 4: Introduction to Self-Attention
Dev.to · Rijul Rajesh 2d ago
Understanding Transformers Part 4: Introduction to Self-Attention
In the previous article, we learned how word embeddings and positional encoding are combined to...
Read article → + Playlist
Understanding Transformers Part 3: How Transformers Combine Meaning and Position
Dev.to · Rijul Rajesh 3d ago
Understanding Transformers Part 3: How Transformers Combine Meaning and Position
In the previous article, we learned how positional encoding is generated using sine and cosine waves....
Read article → + Playlist
Understanding Transformers Part 2: Positional Encoding with Sine and Cosine
Dev.to · Rijul Rajesh 5d ago
Understanding Transformers Part 2: Positional Encoding with Sine and Cosine
In the previous article, we converted words into embeddings. Now let’s see how transformers add...
Read article → + Playlist
Understanding Transformers Part 1: How Transformers Understand Word Order
Dev.to · Rijul Rajesh 6d ago
Understanding Transformers Part 1: How Transformers Understand Word Order
In this article, we will explore transformers. We will work on the same problem as before:...
Read article → + Playlist
Understanding Attention Mechanisms – Part 6: Final Step in Decoding
Dev.to · Rijul Rajesh 1w ago
Understanding Attention Mechanisms – Part 6: Final Step in Decoding
In the previous article, we obtained the initial output, but we didn’t receive the EOS token yet. To...
Read article → + Playlist
Understanding Attention Mechanisms – Part 5: How Attention Produces the First Output
Dev.to · Rijul Rajesh 1w ago
Understanding Attention Mechanisms – Part 5: How Attention Produces the First Output
In the previous article, we stopped at using the softmax function to scale the scores. When we scale...
Read article → + Playlist
Understanding Attention Mechanisms – Part 4: Turning Similarity Scores into Attention Weights
Dev.to · Rijul Rajesh 1w ago
Understanding Attention Mechanisms – Part 4: Turning Similarity Scores into Attention Weights
In the previous article, we just explored the benefits of using dot product instead of cosine...
Read article → + Playlist
Cosine Similarity vs Dot Product in Attention Mechanisms
Dev.to · Rijul Rajesh 1w ago
Cosine Similarity vs Dot Product in Attention Mechanisms
For comparing the hidden states between the encoder and decoder, we need a similarity score. Two...
Read article → + Playlist
Understanding Attention Mechanisms – Part 3: From Cosine Similarity to Dot Product
Dev.to · Rijul Rajesh 2w ago
Understanding Attention Mechanisms – Part 3: From Cosine Similarity to Dot Product
In the previous article, we explored the comparison between encoder and decoder outputs. In this...
Read article → + Playlist
Understanding Attention Mechanisms – Part 2: Comparing Encoder and Decoder Outputs
Dev.to · Rijul Rajesh 2w ago
Understanding Attention Mechanisms – Part 2: Comparing Encoder and Decoder Outputs
In the previous article, we explored the main idea of attention and the modifications it requires in...
Read article → + Playlist
Understanding Attention Mechanisms – Part 1: Why Long Sentences Break Encoder–Decoders
Dev.to · Rijul Rajesh 2w ago
Understanding Attention Mechanisms – Part 1: Why Long Sentences Break Encoder–Decoders
In the previous articles, we understood Seq2Seq models. Now, on the path toward transformers, we need...
Read article → + Playlist
Understanding Seq2Seq Neural Networks – Part 8: When Does the Decoder Stop?
Dev.to · Rijul Rajesh 2w ago
Understanding Seq2Seq Neural Networks – Part 8: When Does the Decoder Stop?
In the previous article, we saw the translation being done. But there is an issue. The decoder does...
Read article → + Playlist
Understanding Teacher Forcing in Seq2Seq Models
Dev.to · Rijul Rajesh 2w ago
Understanding Teacher Forcing in Seq2Seq Models
When we learn about seq2seq neural networks, there is a term we should know called Teacher...
Read article → + Playlist
Understanding Seq2Seq Neural Networks – Part 7: Generating the Output with Softmax
Dev.to · Rijul Rajesh 3w ago
Understanding Seq2Seq Neural Networks – Part 7: Generating the Output with Softmax
In the previous article, we were transforming the outputs to the fully connected layer. A fully...
Read article → + Playlist
Understanding Seq2Seq Neural Networks – Part 6: Decoder Outputs and the Fully Connected Layer
Dev.to · Rijul Rajesh 3w ago
Understanding Seq2Seq Neural Networks – Part 6: Decoder Outputs and the Fully Connected Layer
In the previous article, we were looking at the embedding values in the encoder and the...
Read article → + Playlist
Understanding Seq2Seq Neural Networks – Part 5: Decoding the Context Vector
Dev.to · Rijul Rajesh 3w ago
Understanding Seq2Seq Neural Networks – Part 5: Decoding the Context Vector
In the previous article, we stopped at the concept of the context vector. In this article, we will...
Read article → + Playlist
Understanding Seq2Seq Neural Networks – Part 4: The Encoder and the Context Vector
Dev.to · Rijul Rajesh 3w ago
Understanding Seq2Seq Neural Networks – Part 4: The Encoder and the Context Vector
In the previous article, we stopped with the problem where we wanted to add more weights and biases...
Read article → + Playlist
Understanding Seq2Seq Neural Networks – Part 3: Stacking LSTMs in the Encoder
Dev.to · Rijul Rajesh 3w ago
Understanding Seq2Seq Neural Networks – Part 3: Stacking LSTMs in the Encoder
In the previous article, we created an embedding layer for the input vocabulary In this article, we...
Read article → + Playlist
Understanding Seq2Seq Neural Networks – Part 2: Embeddings for Sequence Inputs
Dev.to · Rijul Rajesh 4w ago
Understanding Seq2Seq Neural Networks – Part 2: Embeddings for Sequence Inputs
In the previous article, we just began with the concept of the sequence to sequence problem, and...
Read article → + Playlist
Understanding Seq2Seq Neural Networks – Part 1: The Seq2Seq Translation Problem
Dev.to · Rijul Rajesh 4w ago
Understanding Seq2Seq Neural Networks – Part 1: The Seq2Seq Translation Problem
There will be problems where we have sequences of one type of thing that need to be translated into...
Read article → + Playlist
Understanding Word2Vec – Part 7: How Negative Sampling Speeds Up Word2Vec
Dev.to · Rijul Rajesh 1mo ago
Understanding Word2Vec – Part 7: How Negative Sampling Speeds Up Word2Vec
In the previous article, we saw the huge number of weights and mentioned about a technnique called...
Read article → + Playlist
Understanding Word2Vec – Part 6: Two Ways Word2Vec Learns Context
Dev.to · Rijul Rajesh 1mo ago
Understanding Word2Vec – Part 6: Two Ways Word2Vec Learns Context
In the previous article, we saw the word embeddings concept, and how training causes similar words to...
Read article → + Playlist
Understanding Word2Vec – Part 5: How Training Creates Word Embeddings
Dev.to · Rijul Rajesh 1mo ago
Understanding Word2Vec – Part 5: How Training Creates Word Embeddings
In the previous article, we visualized the vectors on a graph and saw how we can represent similarity...
Read article → + Playlist
Understanding Word2Vec – Part 4: Visualizing Word Vectors
Dev.to · Rijul Rajesh 1mo ago
Understanding Word2Vec – Part 4: Visualizing Word Vectors
In the previous article, we saw how the next-word prediction is done, and how lack of training is...
Read article → + Playlist