Speeding up Attention Layers
September 11, 2024
Multi-head, Multi-Query & Grouped-Query Attention layers clearly explained. How cache works in the Attention layers
TF-IDF & BM25 Explained
May 1, 2024
TF-IDF and BM25 are two of the most used algorithms in Information Retrieval. In this post we will explain how they work
Precision, Recall and F1 Score metrics
December 21, 2023
Dive into the intuition behind Precision, Recall, and F1 Score. Understand how these metrics balance quality and quantity, from binary problems to object detection.
Load your datasets in Label Studio with JSON
October 10, 2022
Configure local file serving and JSON imports to handle thousands of files in seconds—the production-ready approach.
LoRA - Low-Rank Adaptation of Large Language Models
June 17, 2021
Fine-tuning large language models via trainable rank decomposition matrices
DINO - Emerging Properties in Self-Supervised Vision Transformers
May 24, 2021
Unsupervised visual feature learning using knowledge distillation and transformers
CLIP - Contrastive Language-Image Pre-training
February 26, 2021
Contrastive learning for unified vision-language representations in a shared embedding space
Vision Transformer - An Image is Worth 16x16 Words
October 22, 2020
Google shows how treating image patches as tokens can revolutionize computer vision
DistillBERT - A distilled version of BERT
October 2, 2019
Knowledge distillation compresses BERT: smaller, faster, with almost all performance
RoBERTa - Optimized BERT Pretraining Approach
July 26, 2019
Unlocking the true potential of BERT through rigorous optimization and strategic training choices
BERT - Bidirectional Encoder Representations from Transformers
October 11, 2018
Pre-training bidirectional by jointly conditioning on both left and right context
The Receptive Field in Convolutional Neural Networks
October 10, 2018
Why do architectures use 3x3 filters? It is because of something called Receptive Fields.
GPT1 - Improving Language Understanding by Pre-Training
June 11, 2018
Semi-supervised learning through generative pre-training on unlabeled text and task-specific fine-tuning
SENet - Squeeze and Excitation Networks
September 17, 2017
Introducing channel attention to improve the performance of image classification tasks
Transformer - Attention Is All You Need
June 12, 2017
Demystifying the Transformer architecture, explaining the Encoder, Decoder, and Attention mechanisms block by block with PyTorch implementation
MobileNet v1 - Efficient Convolutional Neural Networks
April 17, 2017
Efficient convolutional neural networks for mobile vision applications
DenseNet - Densely Connected Convolutional Networks
August 25, 2016
Connecting each layer to every other layer to maximize information flow and efficiency
Depthwise Separable Convolutions
August 25, 2016
Same results as standard convolutions with only a fraction of the computational cost. Explore the tricks behind MobileNet and efficient CNNs
