269 skills found · Page 4 of 9
seungjaeryanlee / Implementations NfqNeural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method
haozhg / OmlAI4Science: Efficient data-driven Online Model Learning (OML) / system identification and control
UM-ARM-Lab / Efficient Eng 2 LTLThe associated repo for paper "Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification"
rohanmistry231 / Udemy Tracker FrontendA React-based frontend for a Udemy course tracking platform, offering a responsive interface to monitor course progress and manage learning activities. Built with TypeScript and Tailwind CSS, it integrates seamlessly with a Node.js backend for efficient data handling.
NMS05 / Audio Visual Deception Detection DOLOS Dataset And Parameter Efficient Crossmodal LearningNo description available
Nidhi-Satyapriya / AutoEDA Automated Data Preprocessing ToolkitThe Automated Data Preprocessing Toolkit streamlines the data preprocessing stage in machine learning by automating tasks like handling missing values, encoding categorical features, and normalizing data. With a user-friendly interface for easy dataset uploads, it enhances data quality and improves model performance efficiently.
visresearch / MgcThe official implementation of paper: "Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning"
Zhang-Xuewen / Deep DeePCThis project is source code of paper Deep DeePC: Data-enabled predictive control with low or no online optimization using deep learning by X. Zhang, K. Zhang, Z. Li, and X. Yin. The objective of this work is to learn the DeePC operator using a neural network and bypass online optimization of conventional DeePC for efficient online implementation.
mmdnmz / EyerissEyeriss‑V1 CNN Hardware Accelerator (Verilog) fully parametric. This repository contains the complete Verilog implementation of a functioning CNN hardware accelerator based on the Eyeriss‑V1 architecture. Designed for energy‐efficient deep learning, the design implements the row‑stationary dataflow to maximize data reuse and minimize data movement.
ksluck / CoadaptationRepository replicating the design- and behaviour-adaptation algorithm using reinforcement learning algorithm presented in the paper " Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning"
xiaoxiaoxh / DeformPAM[ICRA 2025] DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment
mistersharmaa / BreastCancerPredictionBreast cancer has the second highest mortality rate in women next to lung cancer. As per clinical statistics, 1 in every 8 women is diagnosed with breast cancer in their lifetime. However, periodic clinical check-ups and self-tests help in early detection and thereby significantly increase the chances of survival. Invasive detection techniques cause rupture of the tumor, accelerating the spread of cancer to adjoining areas. Hence, there arises the need for a more robust, fast, accurate, and efficient non-invasive cancer detection system. Early detection can give patients more treatment options. In order to detect signs of cancer, breast tissue from biopsies is stained to enhance the nuclei and cytoplasm for microscopic examination. Then, pathologists evaluate the extent of any abnormal structural variation to determine whether there are tumors. Architectural Distortion (AD) is a very subtle contraction of the breast tissue and may represent the earliest sign of cancer. Since it is very likely to be unnoticed by radiologists, several approaches have been proposed over the years but none using deep learning techniques. AI will become a transformational force in healthcare and soon, computer vision models will be able to get a higher accuracy when researchers have the access to more medical imaging datasets. The application of machine learning models for prediction and prognosis of disease development has become an irrevocable part of cancer studies aimed at improving the subsequent therapy and management of patients. The application of machine learning models for accurate prediction of survival time in breast cancer on the basis of clinical data is the main objective. We have developed a computer vision model to detect breast cancer in histopathological images. Two classes will be used in this project: Benign and Malignant
vkinakh / ScatsimclrOfficial implementation of paper "ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets", accepted at ICCV 2021 2nd Visual Inductive Priors for Data-Efficient Deep Learning Workshop
bryanwong17 / HiVE MIL[NeurIPS 2025] Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling
SKIL-robotics / SKIL[RSS 2025] SKIL: Semantic Keypoint Imitation Learning for Generalizable, Data‑efficient Robot Manipulation
isarandi / BarecatEfficient data storage format optimized for random-access reads, especially in machine learning workflows
AmarBhatt / Temporal Difference Learning Path PlanningWhen born, animals and humans are thrown into an unknown world forced to use their sensory inputs for survival. As they begin to understand and develop their senses they are able to navigate and interact with their environment. The process in which we learn to do this is called reinforcement learning. This is the idea that learning comes from a series of trial and error where there exists rewards and punishments for every action. The brain naturally logs these events as experiences, and decides new actions based on past experience. An action resulting in a reward will then be higher favored than an action resulting in a punishment. Using this concept, autonomous systems, such as robots, can learn about their environment in the same way. Using simulated sensory data from ultrasonic sensors, moisture sensors, encoders, shock sensors, pressure sensors, and steepness sensors, a robotic system will be able to make decisions on how to navigate through its environment to reach a goal. The robotic system will not know the source of the data or the terrain it is navigating. Given a map of an open environment simulating an area after a natural disaster, the robot will use model-free temporal difference learning with exploration to find the best path to a goal in terms of distance, safety, and terrain navigation. Two forms of temporal difference learning will be tested; off-policy (Q-Learning) and onpolicy (Sarsa). Through experimentation with several world map sizes, it is found that the off-policy algorithm, Q-Learning, is the most reliable and efficient in terms of navigating a known map with unequal states.
cvjena / DeicBenchmark for Data-Efficient Image Classification
SonyResearch / IDEALQuery-Efficient Data-Free Learning from Black-Box Models
OliverStoll / Anomaly Detection Iiot"Federated Learning for Autoencoder-based Condition Monitoring in the Industrial Internet of Things" (IEEE Bigdata) - Exploring resource-efficient & data privacy enabling training at the edge
