Translation Invariance & Equivariance in Convolutional Neural Networks
In this article, we examine two features of convolutional neural networks, translation equivariance and invariance.
2 years ago
Articles
Custom Diffusion with Paperspace
Learn how to customize your diffusion model images with multiple concepts!
2 years ago
Weather forecast using LSTM networks
In this post, we presented the LSTM subclass and used it to construct a weather forecasting model. We proved its effectiveness as a subgroup of RNNs designed to detect patterns in data sequences, including numerical time series data.
2 years ago
Deep Learning Model Explainability with SHAP
In this article, we examine the game theory based approach to explaining outputs of machine learning models: Shapely Additive exPlanations or SHAP. We then demo the technology using sample images in a Gradient Notebook.
2 years ago
Basic Semantic Search with Cohere
In this tutorial, we cover using sentence embeddings for semantic search using Cohere in a Gradient Notebook
2 years ago
Autoencoders and Visual Similarity
In this followup article, we will be taking a look at another beneficial use of autoencoders. We explored how an autoencoder's encoder can be used as a feature extractor with the extracted features then compared using cosine similarity in order to find similar images.
2 years ago
Dense Passage Retrieval in Open-Domain Question Answering
In this article, we talk about what Dense Passage Retrieval is, how it works, and its uses. We also show how to implement it using the Simple Transformers python library in a Gradient Notebook.
2 years ago
Understanding ProGAN
In this article, we will see some GANs improvements over time, then we go through the revolutionary ProGAN paper to see how it works and understand it in depth.
2 years ago
Apply Model Interpretability Algorithms on CIFAR10 Dataset
In this tutorial, we show how to apply model interpretability algorithms from Captum on simple models. We demo building a basic model and use attribution algorithms such as Integrated Gradients, Saliency, DeepLift, and NoiseTunnel to attribute the image's label to the input pixels and visualize it.
2 years ago
