iqrahusan

Tuberculosis_Detection_from_Chest_X_ray_using_Deep_transfer_Learning_-PyTorch-

Rice-Image-Analysis-and-prediction

Deep-Learning-Image-Classification-Models-Based-CNN-or-Attention

This project organizes classic images classification neural networks based on convolution or attention, and writes training and inference python scripts

CNN-KAN

A modified CNN architecture using Kolmogorov-Arnold Networks

bayesianism_is_what_you_dont_need

The best repo showing why bayesianism is a complete misnomer

TorchCP

A Python toolbox for conformal prediction research on deep learning models, using PyTorch.

Skin-Cancer-Classification-Using-CNN-Deep-Learning-Algorithm

As skin cancer is one of the most frequent cancers globally, accurate, non-invasive dermoscopy-based diagnosis becomes essential and promising. A task of our Deep Learning CNN model is to predict seven disease classes with skin lesion images.

Skin-cancer-image-classification

Skin cancer classification using Inceptionv3

Skin-Cancer-Classification-using-Deep-Learning

Classify Skin cancer from the skin lesion images using Image classification. The dataset for the project is obtained from the Kaggle SIIM-ISIC-Melanoma-Classification competition.

SIMPAC-2021-172

CF-4-TSC

Hand-Crafted Convolutional Filters 4 Time Series

CNN-KAN

A modified CNN architecture using Kolmogorov-Arnold Networks

Wav-KAN

The codes to replicate the simulation of the paper :"Wav-KAN: Wavelet Kolmogorov-Arnold Networks"

schrodinger-pca

Schrodinger Principal Component Analysis

BIMT

Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.

pykan

Kolmogorov Arnold Networks

ml-class

Machine learning lessons and teaching projects designed for engineers

Simple-KAN-4-Time-Series

A simple feature-based time series classifier using Kolmogorov–Arnold Networks

Deep-Learning-Roadmap

:satellite: Organized Resources for Deep Learning Researchers and Developers

awesome-tensorflow

TensorFlow - A curated list of dedicated resources http://tensorflow.org

polars_ols

Polars least squares extension - enables fast linear model polar expressions

ConformalImpact

Causal Impact but with MFLES and conformal prediction intervals

deep-learning-papers

Papers about deep learning ordered by task, date. Current state-of-the-art papers are labelled.

labml

🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

LSTM-based-Fetal-Distress-Classification

This project presents the study to empirically evaluate the ability of LSTMs to recognize patterns in multivariate time series of clinical measurements during childbirth that mainly consist of two vital parameters FHR and UC. Specifically, it considers binary classification for diagnosis and prior detection of Fetal Distress before and during childbirth. The proposed solution employs a novel architecture consisting of signal resampling and multiple stacked LSTMs.

LSTM-Gauss-Noise-Attack-TimeSeries-Classification

Gauss Noise Attack Classification with Non Guassian Time Series Data Using LSTM Neural Nets Artitecture with an Accuracy 0f 0.97 and loss function of 0.14. Binary Classification of predicted New Data having accuracy 0.99.

LSTM_Time-series_Classification

This task portrays various LSTM models attempting to classify time-series data from Wireless Sensor Network deployed in real-world office environments. The task is intended as a real-life benchmark in the area of Ambient Assisted Living. This is a binary classification effort which is formed of making predictions to user movements in real-world office environments in the time-series data-set.

multivariate_timeseries_classification

Binary classification of multivariate time series data using LSTM and XGBoost

time-series-classification

Binary Time Series Classification using two different approaches: LSTM with Dropout and LSTM with Attention.