Machine Learning Guide

Discussing Databricks with Ming Chang from Raybeam (part of DEPT®)

Conversation with Dirk-Jan Kubeflow (vs cloud native solutions like SageMaker)

Dirk-Jan Verdoorn - Data Scientist at Dept Agency

Kubeflow. (From the website:) The Machine Learning Toolkit for Kubernetes. The Kubeflow project is dedicated to making deployments of machine learning (ML) workflows on Kubernetes simple, portable and scalable. Our goal is not to recreate other services, but to provide a straightforward way to deploy best-of-breed open-source systems for ML to diverse infrastructures. Anywhere you are running Kubernetes, you should be able to run Kubeflow.

TensorFlow Extended (TFX). If using TensorFlow with Kubeflow, combine with TFX for maximum power. (From the website:) TensorFlow Extended (TFX) is an end-to-end platform for deploying production ML pipelines. When you're ready to move your models from research to production, use TFX to create and manage a production pipeline.

Alternatives:

Airflow MLflow

Chatting with co-workers about the role of DevOps in a machine learning engineer's life

Expert coworkers at Dept

Matt Merrill - Principal Software Developer Jirawat Uttayaya - DevOps Lead The Ship It Podcast (where Matt features often)

Devops tools

Terraform Ansible

Pictures (funny and serious)

Which AWS container service should I use? A visual guide on troubleshooting Kubernetes deployments Public Cloud Services Comparison Killed by Google aCloudGuru AWS curriculum

(Optional episode) just showcasing a cool application using machine learning

Dept uses Descript for some of their podcasting. I'm using it like a maniac, I think they're surprised at how into it I am. Check out the transcript & see how it performed.

Descript The Ship It Podcast How to ship software, from the front lines. We talk with software developers about their craft, developer tools, developer productivity and what makes software development awesome. Hosted by your friends at Rocket Insights. AKA shipit.io Brandbeats Podcast by BASIC An agency podcast with views on design, technology, art, and culture. Explore the new microsite at www.brandbeats.basicagency.com

Show notes: ocdevel.com/mlg/mla-17

Developing on AWS first (SageMaker or other)

Consider developing against AWS as your local development environment, rather than only your cloud deployment environment. Solutions:

Stick to AWS Cloud IDEs (Lambda, SageMaker Studio, Cloud9

Connect to deployed infrastructure via Client VPN

Terraform example YouTube tutorial Creating the keys LocalStack

Infrastructure as Code

Terraform CDK Serverless

Part 2 of deploying your ML models to the cloud with SageMaker (MLOps)

MLOps is deploying your ML models to the cloud. See MadeWithML for an overview of tooling (also generally a great ML educational run-down.)

SageMaker Jumpstart Deploy Pipelines Monitor Kubernetes Neo

Show notes Part 1 of deploying your ML models to the cloud with SageMaker (MLOps)

MLOps is deploying your ML models to the cloud. See MadeWithML for an overview of tooling (also generally a great ML educational run-down.)

SageMaker DataWrangler Feature Store Ground Truth Clarify Studio AutoPilot Debugger Distributed Training

And I forgot to mention JumpStart, I'll mention next time.

Server-side ML. Training & hosting for inference, with a goal towards serverless. AWS SageMaker, Batch, Lambda, EFS, Cortex.dev

Client, server, database, etc.

Use Docker for env setup on localhost & cloud deployment, instead of pyenv / Anaconda. I recommend Windows for your desktop.

Show notes at ocdevel.com/mlg/32.

L1/L2 norm, Manhattan, Euclidean, cosine distances, dot product

Normed distances link

A norm is a function that assigns a strictly positive length to each vector in a vector space. link Minkowski is generalized. p_root(sum(xi-yi)^p). "p" = ? (1, 2, ..) for below. L1: Manhattan/city-block/taxicab. abs(x2-x1)+abs(y2-y1). Grid-like distance (triangle legs). Preferred for high-dim space. L2: Euclidean. sqrt((x2-x1)^2+(y2-y1)^2. sqrt(dot-product). Straight-line distance; min distance (Pythagorean triangle edge) Others: Mahalanobis, Chebyshev (p=inf), etc

Dot product

A type of inner product.
Outer-product: lies outside the involved planes. Inner-product: dot product lies inside the planes/axes involved link. Dot product: inner product on a finite dimensional Euclidean space link

Cosine (normalized dot)

Kmeans (sklearn vs FAISS), finding n_clusters via inertia/silhouette, Agglomorative, DBSCAN/HDBSCAN

NLTK: swiss army knife. Gensim: LDA topic modeling, n-grams. spaCy: linguistics. transformers: high-level business NLP tasks.

matplotlib, Seaborn, Bokeh, D3, Tableau, Power BI, QlikView, Excel

EDA + charting. DataFrame info/describe, imputing strategies. Useful charts like histograms and correlation matrices.

Run your code + visualizations in the browser: iPython / Jupyter Notebooks.

Salary based on location, gender, age, tech... from O'Reilly.

Dimensions, size, and shape of Numpy ndarrays / TensorFlow tensors, and methods for transforming those.

Comparison of different data storage options when working with your ML models.

Some numerical data nitty-gritty in Python.

Reboot on the MLG episode, with more confident recommends.

Introduction to reinforcement learning concepts. ocdevel.com/mlg/29 for notes and resources.

Hyperparameters part 2: hyper-search, regularization, SGD optimizers, scaling. ocdevel.com/mlg/28 for notes and resources

Hyperparameters part 1: network architecture. ocdevel.com/mlg/27 for notes and resources

Community project & intro to Bitcoin/crypto + trading. ocdevel.com/mlg/26 for notes and resources

Convnets or CNNs. Filters, feature maps, window/stride/padding, max-pooling. ocdevel.com/mlg/25 for notes and resources

TensorFlow, Pandas, Numpy, Scikit-Learn, Keras, TensorForce. ocdevel.com/mlg/24 for notes and resources

RNN review, bi-directional RNNs, LSTM & GRU cells. ocdevel.com/mlg/23 for notes and resources

Recurrent Neural Networks (RNNs) and Word2Vec. ocdevel.com/mlg/22 for notes and resources

Natural Language Processing classical/shallow algorithms. ocdevel.com/mlg/20 for notes and resources

Natural Language Processing classical/shallow algorithms. ocdevel.com/mlg/19 for notes and resources

Introduction to Natural Language Processing (NLP) topics. ocdevel.com/mlg/18 for notes and resources

Checkpoint - learn the material offline! ocdevel.com/mlg/17 for notes and resources

Can AI be conscious? ocdevel.com/mlg/16 for notes and resources

Performance evaluation & improvement. ocdevel.com/mlg/15 for notes and resources

Speed run of Anomaly Detection, Recommenders(Content Filtering vs Collaborative Filtering), and Markov Chain Monte Carlo (MCMC). ocdevel.com/mlg/14 for notes and resources

Speed run of Support Vector Machines (SVMs) and Naive Bayes Classifier. ocdevel.com/mlg/13 for notes and resources

Speed-run of some shallow algorithms: K Nearest Neighbors (KNN); K-means; Apriori; PCA; Decision Trees

ocdevel.com/mlg/12 for notes and resources

Languages & frameworks comparison. Languages: Python, R, MATLAB/Octave, Julia, Java/Scala, C/C++. Frameworks: Hadoop/Spark, Deeplearning4J, Theano, Torch, TensorFlow. ocdevel.com/mlg/10 for notes and resources

Deep learning and neural networks. How to stack our logisitic regression units into a multi-layer perceptron. ocdevel.com/mlg/9 for notes and resources

Introduction to the branches of mathematics used in machine learning. Linear algebra, statistics, calculus. ocdevel.com/mlg/8 for notes and resources

Your first classifier: Logistic Regression. That plus Linear Regression, and you're a 101 supervised learner! ocdevel.com/mlg/7 for notes and resources

Discussion on certificates and degrees from Udacity to a Masters degree. ocdevel.com/mlg/6 for notes and resources

Introduction to the first machine-learning algorithm, the 'hello world' of supervised learning - Linear Regression ocdevel.com/mlg/5 for notes and resources

Overview of machine learning algorithms. Infer/predict, error/loss, train/learn. Supervised, unsupervised, reinforcement learning. ocdevel.com/mlg/4 for notes and resources

Show notes at ocdevel.com/mlg/3. Why should you care about AI? Inspirational topics about economic revolution, the singularity, consciousness, and fear.

Show notes at ocdevel.com/mlg/2

Updated! Skip to [00:29:36] for Data Science (new content) if you've already heard this episode.

What is artificial intelligence, machine learning, and data science? What are their differences? AI history.

Hierarchical breakdown: DS(AI(ML)). Data science: any profession dealing with data (including AI & ML). Artificial intelligence is simulated intellectual tasks. Machine Learning is algorithms trained on data to learn patterns to make predictions.

Artificial Intelligence (AI) - Wikipedia

Oxford Languages: the theory and development of computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages.

AlphaGo Movie, very good!

Sub-disciplines

Reasoning, problem solving Knowledge representation Planning Learning Natural language processing Perception Motion and manipulation Social intelligence General intelligence

Applications

Autonomous vehicles (drones, self-driving cars) Medical diagnosis Creating art (such as poetry) Proving mathematical theorems Playing games (such as Chess or Go) Search engines Online assistants (such as Siri) Image recognition in photographs Spam filtering Prediction of judicial decisions Targeting online advertisements Machine Learning (ML) - Wikipedia

Oxford Languages: the use and development of computer systems that are able to learn and adapt without following explicit instructions, by using algorithms and statistical models to analyze and draw inferences from patterns in data.

Data Science (DS) - Wikipedia

Wikipedia: Data science is an interdisciplinary field that uses scientific methods, processes, algorithms and systems to extract knowledge and insights from noisy, structured and unstructured data, and apply knowledge and actionable insights from data across a broad range of application domains. Data science is related to data mining, machine learning and big data.

History Greek mythology, Golums First attempt: Ramon Lull, 13th century Davinci's walking animals Descartes, Leibniz

1700s-1800s: Statistics & Mathematical decision making

Thomas Bayes: reasoning about the probability of events George Boole: logical reasoning / binary algebra Gottlob Frege: Propositional logic 1832: Charles Babbage & Ada Byron / Lovelace: designed Analytical Engine (1832), programmable mechanical calculating machines

1936: Universal Turing Machine

Computing Machinery and Intelligence - explored AI! 1946: John von Neumann Universal Computing Machine 1943: Warren McCulloch & Walter Pitts: cogsci rep of neuron; Frank Rosemblatt uses to create Perceptron (-> neural networks by way of MLP)

50s-70s: "AI" coined @Dartmouth workshop 1956 - goal to simulate all aspects of intelligence. John McCarthy, Marvin Minksy, Arthur Samuel, Oliver Selfridge, Ray Solomonoff, Allen Newell, Herbert Simon

Newell & Simon: Hueristics -> Logic Theories, General Problem Solver Slefridge: Computer Vision NLP Stanford Research Institute: Shakey Feigenbaum: Expert systems GOFAI / symbolism: operations research / management science; logic-based; knowledge-based / expert systems 70s: Lighthill report (James Lighthill), big promises -> AI Winter

90s: Data, Computation, Practical Application -> AI back (90s)

Connectionism optimizations: Geoffrey Hinton: 2006, optimized back propagation Bloomberg, 2015 was whopper for AI in industry AlphaGo & DeepMind

Show notes: ocdevel.com/mlg/1. MLG teaches the fundamentals of machine learning and artificial intelligence. It covers intuition, models, math, languages, frameworks, etc. Where your other ML resources provide the trees, I provide the forest. Consider MLG your syllabus, with highly-curated resources for each episode's details at ocdevel.com. Audio is a great supplement during exercise, commute, chores, etc.

MLG, Resources Guide Gnothi (podcast project): website, Github Tyler's Battlestation What is this podcast? "Middle" level overview (deeper than a bird's eye view of machine learning; higher than math equations) No math/programming experience required

Who is it for

Anyone curious about machine learning fundamentals Aspiring machine learning developers

Why audio?

Supplementary content for commute/exercise/chores will help solidify your book/course-work

What it's not

News and Interviews: TWiML and AI, O'Reilly Data Show, Talking machines Misc Topics: Linear Digressions, Data Skeptic, Learning machines 101 iTunesU issues

Planned episodes

What is AI/ML: definition, comparison, history Inspiration: automation, singularity, consciousness ML Intuition: learning basics (infer/error/train); supervised/unsupervised/reinforcement; applications Math overview: linear algebra, statistics, calculus Linear models: supervised (regression, classification); unsupervised Parts: regularization, performance evaluation, dimensionality reduction, etc Deep models: neural networks, recurrent neural networks (RNNs), convolutional neural networks (convnets/CNNs) Languages and Frameworks: Python vs R vs Java vs C/C++ vs MATLAB, etc; TensorFlow vs Torch vs Theano vs Spark, etc