![sage81564](/img/default-banner.jpg)
- 44
- 91 490
sage81564
United States
Приєднався 28 кві 2011
Nonstationary Data and the Stock Market, Synthetic Minority Oversampling Technique
Nonstationary Data and the Stock Market, Synthetic Minority Oversampling Technique
Переглядів: 22
Відео
Project 2 - Mole or Melanoma Pseudocode Overview (start at 2:00)
Переглядів 2962 роки тому
Start at 2 min to view the pseudocode created in class by one of the teams. Good discussion on an algorithm for asymmetry and jagged border calculations for a skin lesion.
Project 2 - Asymmetry and Border Algorithm Hints
Переглядів 7022 роки тому
For this office hours, Project 2 rubric is reviewed.
Project 2 Overview - Mole or Melanoma?
Переглядів 1842 роки тому
Use python and image processing to implement an algorithm to give the risk level of a skin lesion. This is an introduction to Project 2 in BMEN 207. In addition, gray scale histograms, binary images, and binary large object (BLOB) analysis image processing is introduced.
Project 1 Overview and Hints
Переглядів 1352 роки тому
BMEN 207 Computing for Biomedical Engineering. Project 1 - Calculate SpO2 and HR and Plot During Low Motion
Project 1 - Finding Low Activity Periods Using Accelerometer Data and Moving Window
Переглядів 3572 роки тому
BMEN 207: Computing for Biomedical Engineering class. Topic: how to using a moving window to analyze accelerometer data for low activity periods for heart rate (BPM) and SpO2 calculations.
Using scipy find_peaks to calculate beats per minute (BPM) from a photoplethysomograph
Переглядів 9232 роки тому
Office Hours - Use scipy find_peaks to calculate beats per min from a photoplethysmograph optical heart rate signal.
Office Hours - Project 2 Assignment 2 Overview
Переглядів 3102 роки тому
Overview of how to convert Unix time to human readable time and how to find the most active hour for the Project 2 assignment data.
Python lambda and map functions, pd.read_csv(), and vertically stacking dataframes
Переглядів 1532 роки тому
Learn about Lambda and map functions in python. Office hour include review of homework assignment for loading large set of files using pd.read_csv and stacking or concatenating dataframes vertically.
NutrionIX API Web Services API and Python
Переглядів 8542 роки тому
BMEN 207 Computing for Biomedical Engineer at Texas A&M. Learn how to build a simple python application that uses NutrionIX API for natural language processing(NLP) and calculating calories using written language as an input. Office hours overview of web services homework assignment. Short quiz on numpy vectorization, and pd_read_csv().
Transfer Learning with Keras
Переглядів 2743 роки тому
Learn how to implement transfer learning with Keras machine learning module for Python. Add layers to the ImageNet model. Develop a model that predicts if a cow is standing or not standing using data augmentation from a file directory and transfer learning.
Augmentation and Keras Datagenerators
Переглядів 2183 роки тому
Learn how to use Keras Datagenerators to augment your image data. Use augmentation to create more data for your machine learning models. Augmentation slightly changes or modifies the original data to create new data for the machine learning model.
Regularization and Overfitting
Переглядів 5433 роки тому
Learn how regularization helps prevent overfitting and makes models more generalizable.
Simple Back Propagation in Python from Scratch
Переглядів 1,8 тис.3 роки тому
Demonstrates how to build a back propagation algorithm using a simple neural network in Python. Covers cost functions, gradient descent, and the chain rule.
Activation Functions
Переглядів 1253 роки тому
Learn how activation functions add non-linearity into a neural network.
Back Propagation Understanding the Math
Переглядів 2443 роки тому
Back Propagation Understanding the Math
Anatomy of a neural network (forward propagation from scratch)
Переглядів 2973 роки тому
Anatomy of a neural network (forward propagation from scratch)
Concepts 2 Algorithm Engineering and Deep Learning
Переглядів 1673 роки тому
Concepts 2 Algorithm Engineering and Deep Learning
Concepts 1 Algorithm Engineering and Deep Learning
Переглядів 1773 роки тому
Concepts 1 Algorithm Engineering and Deep Learning
Intro to Algorithm Engineering and Machine Learning (Administrative Info)
Переглядів 2433 роки тому
Intro to Algorithm Engineering and Machine Learning (Administrative Info)
MNIST Handwriting Example-- Code Walkthrough
Переглядів 3243 роки тому
MNIST Handwriting Example Code Walkthrough
Anatomy of a neural network coding example and forward propagation from the ground up
Переглядів 343 роки тому
Anatomy of a neural network coding example and forward propagation from the ground up
LabVIEW File IO, Arrays, and Magnitude Calculation
Переглядів 2,2 тис.4 роки тому
LabVIEW File IO, Arrays, and Magnitude Calculation
LabVIEW For Loop, Graphs, Case Structure, Arrays
Переглядів 9 тис.4 роки тому
LabVIEW For Loop, Graphs, Case Structure, Arrays
I have exactly the same setup, but I don't have the "Figure options" button. Do you know how to enable it?
How can someone be so awesome...
I set up everything properly. In PyCharm all works perfectly. In mobile phone App too... But! - my training data in mobile App and data in python are not the same. I'll wait one day. Maybe they have one update in a day or sth
Nice video sir, Started python after 2-3 weeks and was having some doubts using this API , your video helped greatly
There is a mistake at 2:58. The error in the model for training should actually be less than the test set because it overfits to the training set and minimizes the error in the test set.
I didn't understand your language but you served the purpose Thanks a lot
great video
Can you provide the code in comments
i got this error when trying to open the csv file UnicodeDecodeError: 'utf-8' codec can't decode byte 0xae in position 265: invalid start byte
you helped me thank you.
Come on finish it of DB
If you have an up-to-date pandas installation you can just do a.plot(y='Close') without the need to explicitly create b or import matplotlib.
Awesome, nice explanation
do you know. you helped me thank you.
how to apply it for the column give me the code
My data set is consisting of 20,000 articles but I want to train only the first 100 do u know the command??
df.head(100)
hello there, i am gettin this error ("message": "request requires x-app-id and x-app-key headers") i gave all the headers correctly though.
Great video, I learned a lot. "Thank you for making it.
Awesome!! That's what exactly I needed to know how to make interactive plots in Python
Thank you I need that QT!
Great Xplanations anchor here~
Whoal ny git link ?
There are alternatives to back propagation. The simple evolution algorithm Continuous Gray Code Optimization works very well. You can find the paper online. The mutation operator is random plus or minus a.exp(-p.rnd()). If the neural network weight is constrained between -1 and 1 then a=2 to match the interval. rnd() returns a uniform random between 0 and 1. p is the so called precision and is a problem dependent positive number. It is easy to distribute training over many compute devices. Each device gets the full neural model and part of the training data (which can be local and private.) Each device is sent the same short sparse list of mutations and returns the cost for its part of the training data. The costs are summed and if an improvement an accept message is sent to each device else a reject message. Not much data is moving around per second. The devices could be anywhere on the internet, all around the place. Of course with evolution the faster the neural net the better. Fast Transform fixed filter bank neural nets are a good choice. There is some blog about them
Discrete convolutions, weighted sums and fast transforms like FFT are dot products. Max pooling is switching. ReLU is a switch🤔 f(x)=x is connect, f(x)=0 is disconnect. A light switch in your house is binary on off yet connects or disconnects a continuously variable AC voltage signal. The dot product of a number of dot products is still a dot product. When all the switch states become known in a ReLU net the net collapses to a simple matrix. There is a linear mapping from the input vector to the output vector. There are a lot of metrics you can apply and further math that can be done.
my left ear really enjoyed this
Really helpful thank you