vedant

@ve6ant

Deep Learning Enthusiast

IndiaJoined May 2025

About

Traversing the intricate expanses of multidimensional manifolds, transmuting probabilistic turbulence into infinite sagacity.

Available for

Nothing here yet.

vedant's blogs

The Gradient Loregradientlore.hashnode.dev2 posts

Articles Comments

Recently published

Vvedantgradientlore.hashnode.devJun 25, 2025 · 4 min read

From Thresholds to Probabilities

In the previous post, we looked at Softmax and NLL loss, both critical for output interpretation and learning in Transformers. Now let’s dive into what happens within the network: activation functions. Specifically, GELU. What is GeLU? GeLU, or, Gau...

0

Vvedantgradientlore.hashnode.devMay 30, 2025 · 6 min read

Logits and Likelihoods

In the heart of modern neural networks capable of understanding the sentence semantics and generating thousands of words per second, Transformers, as we call them, lie 2 core mathematical operations that often go unnoticed, namely the Softmax and Neg...

0

vedant

About

Available for

vedant's blogs

Recently published

From Thresholds to Probabilities

Logits and Likelihoods

Search Hashnode

vedant

About

Available for

vedant's blogs

Recently published

From Thresholds to Probabilities

Logits and Likelihoods