A weekly workshop series at ITP to teach machine learning with a focus on deep learning

shekit Last update: Sep 08, 2023

Machine Learning Demystified

A weekly workshop series at NYU ITP to teach machine learning with a focus on deep learning

Week1

Setup Environment

1) Install miniconda

Go to https://conda.io/miniconda.html
Choose Python 3.6 Mac OSX 64-bit (bash installer) and download

2) Open Terminal

Type: bash /path/to/the/file/you/just/downloaded
You can just drag the bash file you download into your terminal window from where you installed it - Press Enter to continue
Review the license and approve the license terms - type in yes and press enter
Press Enter again to confirm the location of install
Type yes when it asks you if the install location should be prepended to PATH
Restart Terminal for changes to take effect
Type: conda info
If it prints out some stuff then it has installed correctly

3) Create an environment

Open Terminal
Type: conda create -n tensor python=3.5.2
Type: y (and press Enter)
This will create a conda environment with the name 'tensor' and python version 3.5.2

4) Activate environment

Open Terminal
Type: source activate tensor
You should see (tensor) prepended before your terminal prompt

5) Install dependencies

Make sure you can see (tensor) prepended before the terminal prompt before proceeding
Type: conda install numpy matplotlib jupyter
Type: y (and press Enter)
Type: pip install nltk gensim keras gym

6) Install Tensor Flow

In the same terminal window type: pip install tensorflow
If the above command gives an error (it shows up in red color in your terminal only then do the following):
- Type: pip install https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-1.0.0-py3-none-any.whl

Tags:

deep-neural-networks

machine-learning

Owner

shekit

GitHub Repository https://github.com/shekit

Programmed the SDN controller to monitor the traffic, predict the traffic behaviour and detect DDOS traffic in the cloud network and mitigate it. Machine learning SVM algorithm was used to predict the malicious traffic in the network, achieved an accuracy of 98% and detection rate of 100%. Technologies Used are, SDN, ML SVM, Openflow, Ryu controller, Python, Mininet, iperf, hping3, linux commands.

Stress classifier with AutoML

This repository presents an automated machine learning approach in Python to create a stress monitoring system with data from devices such as fitness trackers. With the rising popularity of trackers …

Solutions to the 'Applied Machine Learning In Python' Coursera course exercises

PyDeep is a machine learning / deep learning library with focus on unsupervised learning. The library has a modular design, is well documented and purely written in Python/Numpy. This allows you to understand, use, modify, and debug the code easily. Furthermore, its extensive use of unittests assures a high level of reliability and correctness.

Welcome ################################## PyDeep is a machine learning / deep learning library with focus on unsupervised learning. The library has a modular design, is well documented and purely wr…

A 50-Day Guide to Becoming a Data Scientist with Python, SQL, and Machine Learning

Welcome to the Data Science course! Over the next 50 days, you will learn a wide range of topics related to Python programming, data science, and machine learning. These topics will be covered in a v…

splearn: package for signal processing and machine learning with Python. Contains tutorials on understanding and applying signal processing.

This repository contains tutorials on understanding and applying signal processing using NumPy and PyTorch. In order to begin the signal processing adventure, we need to understand what we are dealin…

{Python}: Detect and extract the license plate of vehicles using Machine Learning and Image Processing Techniques

This project aims to utilize Machine Learning and Image Processing techniques to detect/extract license plates of vehicle given an image. This module is aimed to extract features from a license plate…

Python script to generate fake datasets optimized for testing machine learning/deep learning workflows

These datasets also work well when testing against AutoML approaches, as it has several traps just for that use case. The generated datasets have the following properties which test the limits of ML/…

Repo where I recreate some popular machine learning models from scratch in Python

This repository is for educational purposes. While the efficiency of the code or completeness is not as good as the one you could find in a library like sklearn, the simplification of the algorithm a…

Machine learning in Python for stock market and forex market predictions (fully functional)

OPEN-SOURCE PROJECT | Machine learning in Python and MQL4 for stock market and forex market predictions and fully automated trading.