ttungl/feature-selection-for-machine-learning

Stars
18
Rank 1,208,065 (Top 24 %)
Language
Jupyter Notebook
Created over 4 years ago
Updated about 4 years ago

ttungl/feature-selection-for-machine-learning

ttungl

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Statistical-Learning

Deep-Learning

Implemented the deep learning techniques using Google Tensorflow that cover deep neural networks with a fully connected network using SGD and ReLUs; Regularization with a multi-layer neural network using ReLUs, L2-regularization, and dropout, to prevent overfitting; Convolutional Neural Networks (CNNs) with learning rate decay and dropout; and Recurrent Neural Networks (RNNs) for text and sequences with Long Short-Term Memory (LSTM) networks.

Jupyter Notebook

HeteroArchGen4M2S

HeteroArchGen4M2S: An automatic software for configuring and running heterogeneous CPU-GPU architectures on Multi2Sim simulator. This tool is built on top of M2S simulator, it allows us to configure various heterogeneous CPU-GPU architectures (e.g., number of CPU cores, GPU cores, L1$, L2$, memory (size and latency (via CACTI 6.5)), network topologies (currently support 2D-Mesh, customized 2D-Mesh, and Torus networks)...). The output files include the results of network throughput and latency, caches/memory access time, and dynamic power of the cores (can be collected after running McPAT).

RLE-NOC

SDC-term1-Behavioral-Cloning

Built and trained a convolutional neural network to drive the car itself autonomously in a simulator using Tensorflow (backend) and Keras. Experimented with a modified Nvidia architecture. Performed image processing with brightness, shadow augmentation, and flipped images. Used dropout and Adam optimizer to generalize the network for driving multiple tracks. The datasets are used via Udacity's source for training the model. Trained the model on Amazon AWS EC2 platform with GPU instances.

SDC-term1-Advanced-Lane-Finding

Detected highway lane boundaries on a video stream with OpenCV image analysis techniques, including camera calibration matrix, distortion correction, color transforms, gradients, etc., to create a thresholded binary image, a perspective transform to rectify binary image ("birds-eye view"). Detected lane pixels and fit to find the lane boundary, determined the curvature of the lane and vehicle position with respect to center. Warped the detected lane boundaries back onto the original image.

recommender_systems_fkane

Jupyter Notebook

SDC-term1-Finding-Lane-Lines-on-Road

Computer Vision. Detected highway lane lines on a video stream. Used OpenCV image analysis techniques to identify lines, including Hough Transforms and Canny edge detection.

Machine-Learning

Machine learning techniques, such as Linear Regression, Logistic Regression, Neural Networks (feedforward propagation, backpropagation algorithms), Diagnosing Bias/Variance, Evaluating a Hypothesis, Learning Curves, Error Analysis, Support Vector Machines, K-Means Clustering, PCA, Anomaly Detection System, and Recommender System.

Wireless-network-802-11-DCF-MAC

Implemented a 802.11 DCF MAC Protocol operation with Gillbert-Elliot channel model, RTS/CTS exchange, in different network topologies. Used C++ for implementation.

gem5-test

SDC-term2-Model-Predictive-Control

Implemented Model Predictive Control to drive the vehicle around the track (even with additional latency between commands).

leetcode-contests

laceupleetcoding

homepage

data-science-from-scratch-1

ttungl.github.io

kaggle

Public codes for data science competitions on Kaggle.

spark_scala_fkane

ds_salary_prediction

gem5

machine-learning-algorithms-implementation

Price-Dropping-Looker-v1.0

A tool for looking into the price dropped of the Amazon's items. Your "wishlist" items on Amazon will be alerted via your email if those prices are dropped below your expected price, ratings and reviews also are taken into account.

Verilog-VHDL-ALU-16bit

ALU 16-bit design with LCD display VHDL coding on Spartan 3E FPGA Starter kit.

Pingoin

Pingo'in [android app] is created by using a Google maps API. You can build your list of points of interest (POI) on the Googlemap, then the application will scan your map in the preset radius, if your POIs are within this radius, they will be displayed on your screen. Used Java, Eclipse for building the app, and used SVN for merging the code project.

SDC-term1-Traffic-Sign-Classifier

Built and trained a deep neural network to classify traffic signs, using TensorFlow. Experimented with different network architectures. Performed image pre-processing and validation to guard against overfitting. The datasets are collected from the German Traffic Sign for training and random traffic signs downloaded from internet for testing.

Java-Multithreading

Implemented the basis of java multithreading, including the basic threads synchronization, multiple locks using Synchronized Code Blocks, thread pools, countdown latches, Producer-Consumer, Wait and Notify, Low-level Synchronization, Re-entrant Locks, Deadlock, Semaphores, Callable and Future, Interrupting Threads, and Multithreading in Swing with SwingWorker.