Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence (2020-02-12T00:00:00.000000Z)

TL;DR

This survey offers insight into the field of machine learning with Python, taking a tour through important topics to identify some of the core hardware and software paradigms that have enabled it.

Abstract

Smarter applications are making better use of the insights gleaned from data, having an impact on every industry and research discipline. At the core of this revolution lies the tools and the methods that are driving it, from processing the massive piles of data generated each day to learning from and taking useful action. Deep neural networks, along with advancements in classical machine learning and scalable general-purpose graphics processing unit (GPU) computing, have become critical components of artificial intelligence, enabling many of these astounding breakthroughs and lowering the barrier to adoption. Python continues to be the most preferred language for scientific computing, data science, and machine learning, boosting both performance and productivity by enabling the use of low-level libraries and clean high-level APIs. This survey offers insight into the field of machine learning with Python, taking a tour through important topics to identify some of the core hardware and software paradigms that have enabled it. We cover widely-used libraries and concepts, collected together for holistic comparison, with the goal of educating the reader and driving the field of Python machine learning forward.

Authors

S. Raschka

3 papers

Joshua Patterson

1 papers

Corey Nolet

1 papers

TL;DR

Abstract

Authors

References252 items

TensorFlow Quantum: A Software Framework for Quantum Machine Learning

5分で分かる!? 有名論文ナナメ読み：Jacob Devlin et al. : BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding

Towards a Human-like Open-Domain Chatbot

Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition

Advbox: a toolbox to generate adversarial examples that fool neural networks

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Grandmaster level in StarCraft II using multi-agent reinforcement learning

exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models

PaddlePaddle: An Open-Source Deep Learning Platform from Industrial Practice

Silas: High Performance, Explainable and Verifiable Machine Learning

Interpretations are useful: penalizing explanations to align neural networks with prior knowledge

MonoNet: Towards Interpretable Models by Learning Monotonic Features

Towards modular and programmable architecture search

Decision explanation and feature importance for invertible networks

Model-Agnostic Linear Competitors - When Interpretable Models Compete and Collaborate with Black-Box Models

Combining Machine Learning Models using combo Library

Enriching Visual with Verbal Explanations for Relational Concepts - Combining LIME with Aleph

Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro

AutoML: A Survey of the State-of-the-Art

SciPy 1.0: fundamental algorithms for scientific computing in Python

STUMPY: A Powerful and Scalable Python Library for Time Series Data Mining

An Open Source AutoML Benchmark

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

DEEPSEC: A Uniform Platform for Security Analysis of Deep Learning Model

Adversarial Training and Robustness for Multiple Perturbations

Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations

HopSkipJumpAttack: A Query-Efficient Decision-Based Attack

Fast Graph Representation Learning with PyTorch Geometric

A General Approach to Adding Differential Privacy to Iterative Training Procedures

Altair: Interactive Statistical Visualizations for Python

The Limitations of Model Uncertainty in Adversarial Settings

Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses

GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism

Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning

Towards Dependable and Explainable Machine Learning Using Automated Reasoning

Pyro: Deep Universal Probabilistic Programming

signSGD with Majority Vote is Communication Efficient and Fault Tolerant

SNAS: Stochastic Neural Architecture Search

Evaluation Methodology for Attacks Against Confidence Thresholding Models

Torchbearer: A Model Fitting Library for PyTorch

Explaining Black-Box Classifiers with ILP - Empowering LIME with Aleph to Approximate Non-linear Decisions with Relational Rules

T-SNE-CUDA: GPU-Accelerated T-SNE and its Applications to Modern Data

LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks

Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration

Adversarial Robustness Toolbox v0.2.2

BOHB: Robust and Efficient Hyperparameter Optimization at Scale

Auto-Keras: An Efficient Neural Architecture Search System

DARTS: Differentiable Architecture Search

Relational inductive biases, deep learning, and graph networks

Robust Physical-World Attacks on Deep Learning Visual Classification

GenAttack: practical black-box attacks with gradient-free optimization

Towards the first adversarially robust neural network model on MNIST

Dynamic classifier selection: Recent advances and perspectives

MLxtend: Providing machine learning and data science utilities and extensions to Python's scientific computing stack

ADef: an Iterative Algorithm to Construct Adversarial Deformations

Snap ML: A Hierarchical Framework for Machine Learning

Demystifying Parallel and Distributed Deep Learning

PACT: Parameterized Clipping Activation for Quantized Neural Networks

Adversarial Risk and the Dangers of Evaluating Against Weak Attacks

Thermometer Encoding: One Hot Way To Resist Adversarial Examples

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Efficient Neural Architecture Search via Parameter Sharing

Regularized Evolution for Image Classifier Architecture Search

Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification

Universal Language Model Fine-tuning for Text Classification

Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs

Impact of an Extra Layer on the Stacking Algorithm for Classification Problems

Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies

Adversarial Patch

Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

Exploring the Landscape of Spatial Robustness

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

LightGBM: A Highly Efficient Gradient Boosting Decision Tree

Objective Metrics and Gradient Descent Algorithms for Adversarial Examples in Machine Learning