augmented-interpretable-models
gan-vae-pretrained-pytorch
augmented-interpretable-models | gan-vae-pretrained-pytorch | |
---|---|---|
1 | 1 | |
37 | 162 | |
- | - | |
7.4 | 0.0 | |
20 days ago | over 2 years ago | |
Jupyter Notebook | Jupyter Notebook | |
MIT License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
augmented-interpretable-models
-
[R] Emb-GAM: an Interpretable and Efficient Predictor using Pre-trained Language Models
Deep learning models have achieved impressive prediction performance but often sacrifice interpretability, a critical consideration in high-stakes domains such as healthcare or policymaking. In contrast, generalized additive models (GAMs) can maintain interpretability but often suffer from poor prediction performance due to their inability to effectively capture feature interactions. In this work, we aim to bridge this gap by using pre-trained neural language models to extract embeddings for each input before learning a linear model in the embedding space. The final model (which we call Emb-GAM) is a transparent, linear function of its input features and feature interactions. Leveraging the language model allows Emb-GAM to learn far fewer linear coefficients, model larger interactions, and generalize well to novel inputs (e.g. unseen ngrams in text). Across a variety of NLP datasets, Emb-GAM achieves strong prediction performance without sacrificing interpretability. All code is made available on Github.
gan-vae-pretrained-pytorch
-
DCGAN (CIFAR-10) Generating fake images is easy, but how to also output the class label (1 to 10) with the fake generated images?
I have this DCGAN model (https://github.com/csinva/gan-vae-pretrained-pytorch/tree/master/cifar10_dcgan) which generates fake Cifar-10 images. However I also want to get the intended class label output with the fake generated images. How can I do this? This model which I found only generates fake images but doesn't know what class the generated images belong to.
What are some alternatives?
language-planner - Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"
AvatarGAN - Generate Cartoon Images using Generative Adversarial Network
shap - A game theoretic approach to explain the output of any machine learning model. [Moved to: https://github.com/shap/shap]
pytorch-GAT - My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!
scikit-learn-ts - Powerful machine learning library for Node.js – uses Python's scikit-learn under the hood.
AnimeGAN - Generating Anime Images by Implementing Deep Convolutional Generative Adversarial Networks paper
DeepLearning - Contains all my works, references for deep learning
AI-For-Beginners - 12 Weeks, 24 Lessons, AI for All!
handson-ml - ⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 instead.
Real-time-Object-Detection-for-Autonomous-Driving-using-Deep-Learning - My Computer Vision project from my Computer Vision Course (Fall 2020) at Goethe University Frankfurt, Germany. Performance comparison between state-of-the-art Object Detection algorithms YOLO and Faster R-CNN based on the Berkeley DeepDrive (BDD100K) Dataset.
AutoCog - Automaton & Cognition
dnn_from_scratch - A high level deep learning library for Convolutional Neural Networks,GANs and more, made from scratch(numpy/cupy implementation).