Pandas ebookPandas is a Python package providing fast, flexible, and expressive data structures designed to
make working with “relational” or “labeled” data both easy and intuitive. It aims to be the
fundamental high-level building block for doing practical, real world data analysis in Python
|
CNN VisualizationConvolutional Neural Network (CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery.
|
50 years of Data ScienceMore than 50 years ago, John Tukey called for a reformation of academic statistics. In `The
Future of Data Analysis', he pointed to the existence of an as-yet unrecognized science, whose
subject of interest was learning from data, or `data analysis'.
|
YOLOv3: An Incremental ImprovementI managed to make some improvements to YOLO. But, honestly, nothing like super interesting, just a bunch of small changes that make it better. I also helped out with other
people’s research a little.
|
Model Evaluation, Model Selection, and Algorithm SelectionThe correct use of model evaluation, model selection, and algorithm selection
techniques is vital in academic machine learning research as well as in many
industrial settings.
|
Financial Market Time Series Prediction with Recurrent Neural
NetworksLearning from past history is a fudamentality ill-posed. A model may fit past data well but not perform
well when presented with new inputs. With recurrent neural networks (RNNs), we leverage the modeling
abilities of neural networks (NNs) for time series forecastings.
|
Batch Normalization: Accelerating Deep Network Training Training Deep Neural Networks is complicated by the fact
that the distribution of each layer’s inputs changes during
training, as the parameters of the previous layers change.
|
Python numpy reshape and stack cheatsheetPython numpy reshape and stack cheatsheet is a good resource for quick reference of most commonly used methods and functions
|
U-Net: Convolutional Networks for Image SegmentationThere is large consent that successful training of deep net-
works requires many thousand annotated training samples. In this pa-
per, we present a network and training strategy that relies on the strong
use of data augmentation to use the available annotated samples more
efficiently.
|
Xception: Deep Learning with Depthwise Separable ConvolutionsConvolutional neural networks have emerged as the master
algorithm in computer vision in recent years, and developing
recipes for designing them has been a subject of
considerable attention.
|
Important probability distributionsCertain probability distributions occur with such regularity in real-life applications that they have been given their own names. Here, we survey and study basic properties
of some of them.
|
Methods for Detecting Outliers in Univariate Data SetsMost real-world data sets contain outliers that have unusually large or small values when compared with others in the data set. Outliers may cause a negative effect on data analyses, such
as ANOVA and regression, based on distribution assumptions, or may provide useful
information about data when we look into an unusual response to a given study.
|
Good Resource for Python/AI/MlThis resource was deemed open source resource study material provided by our students/learners. If you find this this is not open source study material, please let us know and we can remove it. Please click on the image to verify and download if you can confirm it is public domain study material for Python / AI / ML.
|
Good Resource for Python/AI/MlThis resource was deemed open source resource study material provided by our students/learners. If you find this this is not open source study material, please let us know and we can remove it. Please click on the image to verify and download if you can confirm it is public domain study material for Python / AI / ML.
|
Ray: A Distributed Execution Engine for the Machine Learning EcosystemRay is an open source framework for parallel and distributed Python that can make numeric computations many times faster. Ray takes the existing concepts of functions and classes and translates them to the distributed setting as tasks and actors.
|
|