Machine Learning

A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet

Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet TL;DR We replace the attention layer in a vision transformer with a feed-forward layer and find that it still works quite well on ImageNet. Abstract The strong performance of vision transformers on image classification and other vision tasks is often attributed to the design of their multi-head attention layers. However, the extent to which attention is responsible for this strong performance remains unclear. In this […]

Read more
Data Analysis

A scikit-learn-compatible module for estimating prediction intervals

MAPIE MAPIE allows you to easily estimate prediction intervals on single-output data using your favourite scikit-learn-compatible regressor. Prediction intervals output by MAPIE encompass both aleatoric and epistemic uncertainty and are backed by strong theoretical guarantees [1]. Requirements Python 3.7+ MAPIE stands on the shoulders of giant. Its only internal dependency is scikit-learn. Installation Install via pip: pip install mapie To install directly from the github repository : pip install git+https://github.com/simai-ml/MAPIE Quickstart Let us start with a basic regression problem. Here, […]

Read more
Robot

A simple introductory discord bot that give introduction

introductoryBot This is a very very very simple introductory dicord bot that give introduction. Type “!intro” to call the bot. It is made in Python 3.9.0. It’s very customizable. Step 1: Go to https://discord.com/developers/applications and click on new application Step 2: Give it a name Step 3: Go to bot and click add bot. Step 4 Go to OAuth2 and select the scope type as ‘bot’ in OAuth2 URL Generator Step 5 Select permissions as you want(Make sure that you […]

Read more
RESTful API

Python client for the Datadog API

datadog-api-client-python This repository contains a Python API client for the Datadog API. The code is generated using openapi-generator and apigentools. Requirements Building and using the API client library requires Python 3.6+. Installation To install the API client library, simply execute: pip install datadog-api-client Getting Started Please follow the installation instruction and execute the following Python code: import os from dateutil.parser import parse as dateutil_parser import datadog_api_client.v1 from datadog_api_client.v1.api import aws_integration_api from datadog_api_client.v1.models import * from pprint import pprint # Defining […]

Read more
RESTful API

A Python wrapper for Matrix Synapse admin API

Synapse-admin-api-python A Python wrapper for Matrix Synapse admin API This library now supports up to Synapse 1.34.0, any Admin API introduced after 1.34.0 may not be included in this version. However, newer changes to Admin API are planned to be included in this library. For planned update, see TODO.md. In the future, the version numbering convention will follow the version this library up to, for example, if this library supports up to 1.34.0, then the version number of this library […]

Read more
Database

A Simple And Efficent JSON based DataBase for Python

pysonDB A Simple, Lightweight, Efficent JSON based DataBase for Python. The current stable version is v0.6.0 pip install pysondb==0.6.0 Features Lightweight JSON based database. Supports CRUD commands. No Database drivers required. Unique ID assigned for each JSON document added. Strict about Schema of data added. Inbuilt CLI to delete,display,create JSON database. from pysondb import dba=db.getDb(“path/to/json.json”)a.addMany([{“name”:”pysondb”,”type”:”DB”},{“name”:”pysondb-cli”,”type”:”CLI”}])a.getAll()[{“name”:”pysondb”,”type”:”DB”},{“name”:”pysondb-cli”,”type”:”CLI”}] See its simple.. Install pip install pysondb Create a database You can create a database using CLI. pysondb create database_name Or in the python file. […]

Read more
Images

Focused on having various feature implementations of OpenCV in Python

Image Processing OpenCV This repository is focused on having various feature implementation of OpenCV in Python. The aim is to have a minimal implementation of all OpenCV features together, under one roof. This repository is focused on having various feature implementations of OpenCV in Python. About OpenCV: OpenCV (Open Source Computer Vision Library) is an open-source computer vision and machine learning software library. OpenCV was built to provide a common infrastructure for computer vision applications and to accelerate the use […]

Read more
NLP

Language Modelling as a Multi-Task Problem

April 18, 2021 By: Lucas Weber, Jaap Jumelet, Elia Bruni, Dieuwke Hupkes Abstract In this paper, we propose to study language modeling as a multi-task problem, bringing together three strands of research: multitask learning, linguistics, and interpretability. Based on hypotheses derived from linguistic theory, we investigate whether language models adhere to learning principles of multi-task learning during training. We showcase the idea by analysing the generalization behavior of language models during learning of the linguistic concept of Negative Polarity Items […]

Read more
NLP

Co-evolution of language and agents in referential games

Abstract Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental for the shape of human language: that it must be learnable by new language learners. Cogswell et al. (2019) introduced cultural transmission within referential games through a changing population of agents to constrain the emerging language to be learnable. However, the resulting languages […]

Read more
NLP

Quality Estimation without Human-labeled Data

April 21, 2021 By: Yi-Lin Tuan, Ahmed El-Kishky, Adithya Renduchintala, Vishrav Chaudhary, Francisco Guzmán, Lucia Specia Abstract Quality estimation aims to measure the quality of translated content without access to a reference translation. This is crucial for machine translation systems in real-world scenarios where high-quality translation is needed. While many approaches exist for quality estimation, they are based on supervised machine learning requiring costly human labelled data. As an alternative, we propose a technique that does not rely on examples […]

Read more
1 … 649 650 651 652 653 … 936