📒
📒
📒
📒
Machine & Deep Learning Compendium
Search…
The Machine & Deep Learning Compendium
Types Of Machine Learning
Data Science
Data Science Tools
Management
Data Science Management
Calculus
Probability & Statistics
Probability
Feature Types
Features
Calibration
Multi Label Classification
Distribution
Distribution Transformation
Information Theory
Game Theory
Datasets
Dataset Confidence
Normalization & Scaling
Regularization
Validation
Meta Learning
Evaluation Metrics
Benchmarking
Hyper Parameter Optimization
Multi CPU Processing
Algorithms 101
Training Strategies
Classic Machine Learning
Label Algorithms
Clustering Algorithms
Anomaly Detection
Decision Trees
Active Learning Algorithms
Linear Separator Algorithms
Ensembles
Reinforcement Learning
Incremental Learning
Dimensionality Reduction Methods
Genetic Algorithms & Genetic Programming
Learning Classifier Systems
Recommender Systems
Timeseries
Fourier Transform
Digital Signal Processing (DSP)
Propensity Score Matching
Natural Language Processing
Graphs
Deep Learning
Experimental Design
Product
Business Domains For Data Science
MLOPs Engineering
Model Formats
Data Engineering
Powered By GitBook
Data Science

LIFE CYCLE

​Microsoft on Team DS Lifecycle - "The Team Data Science Process (TDSP) is an agile, iterative data science methodology to deliver predictive analytics solutions and intelligent applications efficiently. TDSP helps improve team collaboration and learning by suggesting how team roles work best together. TDSP includes best practices and structures from Microsoft and other industry leaders to help toward successful implementation of data science initiatives. The goal is to help companies fully realize the benefits of their analytics program.
This article provides an overview of TDSP and its main components. We provide a generic description of the process here that can be implemented with different kinds of tools. A more detailed description of the project tasks and roles involved in the lifecycle of the process is provided in additional linked topics. Guidance on how to implement the TDSP using a specific set of Microsoft tools and infrastructure that we use to implement the TDSP in our teams is also provided."
ML systems is more than ML code. Google.
ML systems is more than ML code. Google.
"When I used to do consulting, I’d always seek to understand an organization’s context for developing data projects, based on these considerations:
  • Strategy: What is the organization trying to do (objective) and what can it change to do it better (levers)?
  • Data: Is the organization capturing necessary data and making it available?
  • Analytics: What kinds of insights would be useful to the organization?
  • Implementation: What organizational capabilities does it have?
  • Maintenance: What systems are in place to track changes in the operational environment?
  • Constraints: What constraints need to be considered in each of the above areas?"

WORKFLOWS

  1. 1.
    ​kaggle​

PLATFORMS

STACK

Being a DS / Researcher

  1. 1.
    ​A day in a life​
  2. 2.
    ​Advice for a ds, business kpi are not research kpi, etc
  3. 3.
    ​Review of deep learning papers and co authorship​
  4. 4.
    Full stack DS Uri Weiss​
    ​
    ​
    by Uri Weiss. wrong credits? please contact me.
  5. 5.
    ​ML practices for a DS​

Team Building / Group Cohesion

  1. 1.
    ​DS vs DA vs MLE - the most intensive diagram post ever. This is the motherload of figure references.
References:
​1, 2, 3, 4, 5, 6, 7, 8, 9, 10

Culture

  1. 1.
    ​Netflix culture
  2. 2.
    ​Reed hastings on netflix' keeper test - "netflixs-keeper-test-is-the-secret-to-a-successful-workforce"
    1. 1.
      ​response 1​
  3. 3.
    ​

Agile for data-science-research

Building Data/DS teams

YOUTUBE COURSES

Deep learning Course

  1. 1.
    ​Kadenze - deep learning tensor flow - Histograms for (Image distribution - mean distribution) / std dev, are looking quite good.
  2. 2.
    ​deep learning with keras​

Machine Learning Courses

NLP Courses

  1. 1.
    ​spacy 101
  2. 2.
    ​gensim, 2, gensim notebooks
  3. 3.
    ​nltk, 2​
  4. 4.
    ​yandex​
  5. 5.
    lena voita​
​ ​
​

Predictive Analytics Course

​Syllabus​

BOOKS & NOTEBOOKS

  1. 1.
    ​Machine learning design patterns, git notebooks!, medium​
    1. 1.
      ​DP1 - transform Moving an ML model to production is much easier if you keep inputs, features, and transforms separate
    2. 2.
      ​DP2 - checkpoints Saving the intermediate weights of your model during training provides resilience, generalization, and tunability
    3. 3.
      ​DP3 - virtual epochs Base machine learning model training and evaluation on total number of examples, not on epochs or steps
    4. 4.
      ​DP4 - keyed predictions Export your model so that it passes through client keys
    5. 5.
      ​DP5 - repeatable sampling use the hash of a well distributed column to split your data into training, validation, and testing
  2. 2.
    ​Gensim notebooks - from w2v, doc2vec to nmf, lda, pca, sklearn api, cosine, topic modeling, tsne, etc.
  3. 3.
    ​Deep learning with python - francois chollet, deep learning & vision git notebooks!, official notebooks.
  4. 4.
    Yandex school, nlp notebooks​
  5. 5.
    ​Machine learning engineering book (i.e., data science)
  6. 6.
    ​Interpretable Machine Learning book​
  7. 7.
    ​

COST

  1. 1.
    ​GPT2/3​

Patents

General Advice

(really good) Practical advice for analysis of large, complex data sets - distributions, outliers, examples, slices, metric significance, consistency over time, validation, description, evaluation, robustness in measurement, reproducibility, etc.
Previous
N-Shot Learning
Next
Data Science Tools
Last modified 2mo ago
Copy link
Outline
LIFE CYCLE
WORKFLOWS
PLATFORMS
STACK
Being a DS / Researcher
Team Building / Group Cohesion
Culture
Agile for data-science-research
SOTA AND CURRENT TRENDS SUMMARIES
Building Data/DS teams
YOUTUBE COURSES
Deep learning Course
Machine Learning Courses
NLP Courses
Predictive Analytics Course
BOOKS & NOTEBOOKS
COST
Patents
General Advice