269 skills found · Page 8 of 9
dgaddy / Environment LearningCode for "Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following"
0sparsh2 / Music Genre ClassifierImplementing different machine learning models on input music data and finding the most efficient method.
ykumargupta / Power Theft DetectionMachine Learning Algorithm for Efficient Power Theft Detection using Smart Meter Data
topsecretagent007 / Solana Token AI AgentA Solana-based AI agent that automates token management and trading decisions. It leverages on-chain data and machine learning to optimize strategy execution, enabling smarter and more efficient DeFi interactions.
ycd2016 / Acaioc2Highly Efficient Memory Failure Prediction using Mcelog-based Data Mining and Machine Learning
Raad-Labs / Raad VideoA high-performance video loading library for machine learning, designed for efficient training data preparation.
roussel-ryan / Gpsr 6d PaperData and code files related to "Efficient 6-dimensional phase space reconstruction using generative machine learning" paper in PRAB
m2aia / Pym2aiapyM²aia is a Python package for memory-efficient access and processing of mass spectrometry image data. The I/O functionality is derived from the interactive desktop application M²aia. Special features are the batch generator utilities for deep learning applications.
chenyuanTKCY / KDSelectorKDSelector proposes a novel knowledge-enhanced and data-efficient framework for learning a neural network-based model selector in the context of time series anomaly detection.
liyan2015 / AdaptiveBatchHEAn adaptive batch homomorphic encryption framework for cross-device Federated Learning, which determines cost-efficient and sufficiently secure encryption strategies for clients with heterogeneous data and system capabilities.
mdzaheerjk / NumpyA structured NumPy practice repository showcasing hands-on learning through Jupyter notebooks. It covers array creation, indexing, slicing, reshaping, broadcasting, and numerical operations. Built to strengthen core foundations required for Data Science, Machine Learning, and efficient scientific computing in Python.
yannTrm / Resnet 1DThis GitHub repository contains a specialized implementation of 1D Residual Networks (ResNets) for sequence data classification tasks. With tailored architectures and various ResNet variants, it offers efficient learning from 1D sequential data, making it ideal for applications such as time series analysis and sensor data classification.
Zoybzo / FedEraser CodeCode for the paper "FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models". Get from the link in the paper. The link is: https://www.dropbox.com/s/1lhx962axovbbom/FedEraser-Code.zip?dl=0
csce585-mlsystems / Cae CylinderA deep learning model combining a Convolutional Autoencoder and LSTM to predict unsteady flow fields around a 2D cylinder, trained on CFD data from Basilisk. Designed for efficient reconstruction and short-term prediction of velocity and pressure fields.
janmayer15 / Optimizing Production Profitability Through Deep Reinforcement Learning Driven Quality PredictionReinforcement Learning, specifically Deep Q-Networks, was applied to semiconductor manufacturing data to efficiently identify substandard products, with a model optimized using the F1-Metric achieving 87% accuracy and a 22.4% time-saving, highlighting RL's potential in enhancing manufacturing processes.
suryakant1811 / CPPDive into the world of C++! This repository chronicles my journey through learning C++ and mastering Data Structures & Algorithms (DSA). 💡 From basics to advanced implementations, join me as I write efficient, elegant, and optimized code. Let's decode DSA one step at a time!
Jeshima / IndiaFightsCorona Lockdown Covid19 Twitter Sentiment AnalysisI qt worked on corona virus tweet streams mam With hashtags #covid19,#indiafightscorona,#lockdown I did generate the dastset from the stream and procesed according to the working of deep learning algorithms work flow. I reframed my datset with 2 parameters-- tweets full text and sentiment score and worked on 4 algorithms mam. SET 1- DEEP LEARNING ALGOTITHMS: 1.CNN -(used 1csv with train_test_split method ) Accuracy-0.73368 2.LSTM- (used 2csv file seperate for trainingand testing) Training accuracy-0.9457,loss-0.1605 Testing accuracy-0.6557,loss-0.3442 3.FFNN-( used 2csv file seperate for trainingand testing) Training accuracy-0.28,loss-622.3 Testing accuracy-0.14893,loss-141.82 4.ANN with TFIDF Vectorizer(used 1 csv wth train_test_split) The different Ann epoches and models with different learning rate and different drop out value ,Training accuracy ranged btween 0.4752 to 0.6270 and the Validation accuracy ranged 0.2353 constantly On comparing the above 4 algorithms I came to a conclusiom with my understanding Sentiment analysis in tweets can be done efficiently in this order. CNN > LSTM > ANN > FFNN. SET 2-MACHINE LEARNING I did try with Linear Support vector Classifier --1 csv train_test_split method Training accuracy - 0.6666 Testing accuracy(f1score)-0.59471 And with Naive bayes classifier--1 csv train_test_split method Training accuracy - 0.64 Test accuracy -0.5486 SET 3- MODEL CLASSIFICATIONS: I compared my datasets efficiency with 4 models . The accuracies of the model classificatiom are: 1.Baseline Model - 62.86% 2.Reduces Model-65.71% 3.Regularized Model-66.86% 4.Dropout Model-67.43% Efficient modeling order for tweet data-set Dropout model > Regularized model > Reduced model > Baseline model .
CambridgeIIS / Gesture SpotterIn this paper we examine the task of key gesture spotting: accurate and timely online recognition of hand gestures. We specifically seek to address two key challenges faced by developers when integrating key gesture spotting functionality into their applications. These are: i) achieving high accuracy and zero or negative activation lag with single-time activation; and ii) avoiding the requirement for deep domain expertise in machine learning. We address the first challenge by proposing a key gesture spotting architecture consisting of a novel gesture classifier model and a novel single-time activation algorithm. This key gesture spotting architecture was evaluated on four separate hand skeleton gesture datasets, and achieved high recognition accuracy with early detection. We address the second challenge by encapsulating different data processing and augmentation strategies, as well as the proposed key gesture spotting architecture, into a graphical user interface and an application programming interface. Two user studies demonstrate that developers are able to efficiently construct custom recognizers using both the graphical user interface and the application programming interface.
pnguenda / Pandas Challenge# Pandas Homework - Pandas, Pandas, Pandas ## Background The data dive continues! Now, it's time to take what you've learned about Python Pandas and apply it to new situations. For this assignment, you'll need to complete **one of two** (not both) Data Challenges. Once again, which challenge you take on is your choice. Just be sure to give it your all -- as the skills you hone will become powerful tools in your data analytics tool belt. ### Before You Begin 1. Create a new repository for this project called `pandas-challenge`. **Do not add this homework to an existing repository**. 2. Clone the new repository to your computer. 3. Inside your local git repository, create a directory for the Pandas Challenge you choose. Use folder names corresponding to the challenges: **HeroesOfPymoli** or **PyCitySchools**. 4. Add your Jupyter notebook to this folder. This will be the main script to run for analysis. 5. Push the above changes to GitHub or GitLab. ## Option 1: Heroes of Pymoli  Congratulations! After a lot of hard work in the data munging mines, you've landed a job as Lead Analyst for an independent gaming company. You've been assigned the task of analyzing the data for their most recent fantasy game Heroes of Pymoli. Like many others in its genre, the game is free-to-play, but players are encouraged to purchase optional items that enhance their playing experience. As a first task, the company would like you to generate a report that breaks down the game's purchasing data into meaningful insights. Your final report should include each of the following: ### Player Count * Total Number of Players ### Purchasing Analysis (Total) * Number of Unique Items * Average Purchase Price * Total Number of Purchases * Total Revenue ### Gender Demographics * Percentage and Count of Male Players * Percentage and Count of Female Players * Percentage and Count of Other / Non-Disclosed ### Purchasing Analysis (Gender) * The below each broken by gender * Purchase Count * Average Purchase Price * Total Purchase Value * Average Purchase Total per Person by Gender ### Age Demographics * The below each broken into bins of 4 years (i.e. <10, 10-14, 15-19, etc.) * Purchase Count * Average Purchase Price * Total Purchase Value * Average Purchase Total per Person by Age Group ### Top Spenders * Identify the the top 5 spenders in the game by total purchase value, then list (in a table): * SN * Purchase Count * Average Purchase Price * Total Purchase Value ### Most Popular Items * Identify the 5 most popular items by purchase count, then list (in a table): * Item ID * Item Name * Purchase Count * Item Price * Total Purchase Value ### Most Profitable Items * Identify the 5 most profitable items by total purchase value, then list (in a table): * Item ID * Item Name * Purchase Count * Item Price * Total Purchase Value As final considerations: * You must use the Pandas Library and the Jupyter Notebook. * You must submit a link to your Jupyter Notebook with the viewable Data Frames. * You must include a written description of three observable trends based on the data. * See [Example Solution](HeroesOfPymoli/HeroesOfPymoli_starter.ipynb) for a reference on expected format. ## Option 2: PyCitySchools  Well done! Having spent years analyzing financial records for big banks, you've finally scratched your idealistic itch and joined the education sector. In your latest role, you've become the Chief Data Scientist for your city's school district. In this capacity, you'll be helping the school board and mayor make strategic decisions regarding future school budgets and priorities. As a first task, you've been asked to analyze the district-wide standardized test results. You'll be given access to every student's math and reading scores, as well as various information on the schools they attend. Your responsibility is to aggregate the data to and showcase obvious trends in school performance. Your final report should include each of the following: ### District Summary * Create a high level snapshot (in table form) of the district's key metrics, including: * Total Schools * Total Students * Total Budget * Average Math Score * Average Reading Score * % Passing Math (The percentage of students that passed math.) * % Passing Reading (The percentage of students that passed reading.) * % Overall Passing (The percentage of students that passed math **and** reading.) ### School Summary * Create an overview table that summarizes key metrics about each school, including: * School Name * School Type * Total Students * Total School Budget * Per Student Budget * Average Math Score * Average Reading Score * % Passing Math (The percentage of students that passed math.) * % Passing Reading (The percentage of students that passed reading.) * % Overall Passing (The percentage of students that passed math **and** reading.) ### Top Performing Schools (By % Overall Passing) * Create a table that highlights the top 5 performing schools based on % Overall Passing. Include: * School Name * School Type * Total Students * Total School Budget * Per Student Budget * Average Math Score * Average Reading Score * % Passing Math (The percentage of students that passed math.) * % Passing Reading (The percentage of students that passed reading.) * % Overall Passing (The percentage of students that passed math **and** reading.) ### Bottom Performing Schools (By % Overall Passing) * Create a table that highlights the bottom 5 performing schools based on % Overall Passing. Include all of the same metrics as above. ### Math Scores by Grade\*\* * Create a table that lists the average Math Score for students of each grade level (9th, 10th, 11th, 12th) at each school. ### Reading Scores by Grade * Create a table that lists the average Reading Score for students of each grade level (9th, 10th, 11th, 12th) at each school. ### Scores by School Spending * Create a table that breaks down school performances based on average Spending Ranges (Per Student). Use 4 reasonable bins to group school spending. Include in the table each of the following: * Average Math Score * Average Reading Score * % Passing Math (The percentage of students that passed math.) * % Passing Reading (The percentage of students that passed reading.) * % Overall Passing (The percentage of students that passed math **and** reading.) ### Scores by School Size * Repeat the above breakdown, but this time group schools based on a reasonable approximation of school size (Small, Medium, Large). ### Scores by School Type * Repeat the above breakdown, but this time group schools based on school type (Charter vs. District). As final considerations: * Use the pandas library and Jupyter Notebook. * You must submit a link to your Jupyter Notebook with the viewable Data Frames. * You must include a written description of at least two observable trends based on the data. * See [Example Solution](PyCitySchools/PyCitySchools_starter.ipynb) for a reference on the expected format. ## Hints and Considerations * These are challenging activities for a number of reasons. For one, these activities will require you to analyze thousands of records. Hacking through the data to look for obvious trends in Excel is just not a feasible option. The size of the data may seem daunting, but pandas will allow you to efficiently parse through it. * Second, these activities will also challenge you by requiring you to learn on your feet. Don't fool yourself into thinking: "I need to study pandas more closely before diving in." Get the basic gist of the library and then _immediately_ get to work. When facing a daunting task, it's easy to think: "I'm just not ready to tackle it yet." But that's the surest way to never succeed. Learning to program requires one to constantly tinker, experiment, and learn on the fly. You are doing exactly the _right_ thing, if you find yourself constantly practicing Google-Fu and diving into documentation. There is just no way (or reason) to try and memorize it all. Online references are available for you to use when you need them. So use them! * Take each of these tasks one at a time. Begin your work, answering the basic questions: "How do I import the data?" "How do I convert the data into a DataFrame?" "How do I build the first table?" Don't get intimidated by the number of asks. Many of them are repetitive in nature with just a few tweaks. Be persistent and creative! * Expect these exercises to take time! Don't get discouraged if you find yourself spending hours initially with little progress. Force yourself to deal with the discomfort of not knowing and forge ahead. Consider these hours an investment in your future! * As always, feel encouraged to work in groups and get help from your TAs and Instructor. Just remember, true success comes from mastery and _not_ a completed homework assignment. So challenge yourself to truly succeed! ### Copyright Trilogy Education Services © 2019. All Rights Reserved.
lry-bupt / UCB MARLThe simulation codes of a provably efficient multi-agent reinforcement learning algorithm with a near-optimal regret bound in industrail data collection.
