SSummlit

Public profile

@sakibbai

Learning maps and explanations shared with the Summlit community.

Maps
3
Explanations
10
Learners
1
Helpful
0

Public maps

3
  1. Attention is All You Need

    Not ADHD

    Literature quest centered on Attention is All You Need.

    11 concepts · 6 explanations
    Open →
  2. LoRA: Low-Rank Adaptation of Large Language Models

    Lora

    Literature quest centered on LoRA: Low-Rank Adaptation of Large Language Models.

    9 concepts · 4 explanations
    Open →
  3. TinySV: Speaker Verification in TinyML with On-device Learning

    Quest: TinySV: Speaker Verification in TinyML with On-device Learning

    Literature quest centered on TinySV: Speaker Verification in TinyML with On-device Learning.

    10 concepts · 1 learner
    Open →

Explanations

10
  1. foundational

    Linear Algebra Basics

    The study of vectors, vector spaces, matrix operations, and dot products used to represent and transform data.

    3 reads
  2. foundational

    Softmax Function

    An activation function that normalizes a vector of real numbers into a probability distribution summing to one.

    Published explanation
  3. foundational

    Word Embeddings

    Dense vector representations of discrete tokens where geometric distance reflects semantic similarity.

    Published explanation
  4. core

    Residual Connections

    A network design where a layer's input is added directly to its output, creating shortcut paths for gradient flow.

    Published explanation
  5. core

    Dot-Product Attention

    An attention mechanism computing alignment scores by taking the scalar product of query and key vectors.

    Published explanation
  6. core

    Positional Encoding

    A method of adding deterministic or learned order signal vectors to input embeddings.

    Published explanation
  7. advanced

    Transformer Architecture

    An encoder-decoder model architecture relying entirely on self-attention mechanisms, bypassing recurrence and convolutions.

    Published explanation
  8. foundational

    Gradient Descent and Backpropagation

    An optimization algorithm that calculates loss gradients via the chain rule to iteratively update neural network weights.

    1 reads
  9. core

    Intrinsic Dimensionality of Model Updates

    The property stating that effective learning in high-dimensional parameter spaces can be captured within a much lower-dimensional subspace.

    Published explanation
  10. foundational

    Matrix Rank and Low-Rank Decomposition

    The measure of non-redundant dimensions in a matrix and its factorization into smaller matrices of reduced dimensionality.

    Published explanation
@sakibbai · Summlit · Summlit