Deep Learning, AI and Natural Language Processing: quizzes, mind maps and notes

Top Deep Learning, AI and Natural Language Processing resources

Quizzes

60 questions
Unstructured Data Analytics Quizes Kelly Cronin
14 questions
Module 6 Review Which of the following is a correct validation fit statistic when predicting Decisions? Nick Feldman
10 questions
Machine Leaning / AI Which of the following statement(s) correctly represents a real neuron? BHUPEN SHARMA

Mind maps

See all 28 mind maps

Flashcards

Flowcharts

Notes

Classification and vector spaces Sentiment analysis :  say you have 1000 product reviews : go through the product review and classify how much % is good and how much is bad?   In the first week, you'll learn how to represent text as a vecto... Mukundhan Srinivasan
RNN and LSTM Load required libraries : import pandas as pd import numpy as np import matplotlib.pyplot as plt from keras.models import Sequential from keras.layers import Dense, SimpleRNN Generating sample dataset   # convert... Kaveri Kale
Ideas to improve accuracy in Neural Networks Extension for Google Chrome: Fatkun Batch Download da imagem, download many images from a website. Create your Dataset. How to improve Deep Learning: https://machinelearningmastery.com/improve-deep-learning-... Bernardo Costa
[AI] #6 Analytics SIN YEE YAP

Slides

Topics in Deep Learning, AI and Natural Language Processing

Machine Learning Fundamentals5 Neural Networks and Deep Learning6 Neural Network Architectures6 Text Preprocessing and Representation7 Machine Learning Models for NLP5 Text Classification and Sentiment Analysis8

About Deep Learning, AI and Natural Language Processing

GoConqr Original

What this unit covers

The unit sits in the Machine Learning and Artificial Intelligence strand of Databases and data science. It mixes broad machine learning ideas with neural networks and language processing, so you can move between the two.

Deep learning models: mind maps on DCGAN, Variational Auto-Encoder (VAE) and Sparse Autoencoder, plus notes on RNN and LSTM.
Language processing: maps on NLP, NLU, Tokenization and eScience Neural NLP, which lists tasks such as semantic role labelling and machine translation.
Text features: maps on lexical, syntactic and semantic features. The lexical one covers type-token ratio and hapax legomena.

Where to start

Begin with the Machine Learning mind maps. They separate supervised, unsupervised and reinforcement learning, and name methods such as classification, regression, clustering and k-means. Then open the flashcard deck DAtaAnalyticsAIMachineLearningAMIA22, which asks you to define data science, artificial intelligence, expert systems, machine learning and deep learning.

Moving into language

Next, take the NLU flashcards. They ask you to name statistical and probabilistic NLP methods and to describe generative and discriminative models. The Week 10 - Sentiment Analysis deck follows on, with questions on how sentiment analysis works and what makes it hard. The flow chart preprocessing flowchart and the Word Embedding approaches slide set help you see how raw text becomes input for a model.

Using quizzes with maps

Try Unstructured Data Analytics Quizes after a few maps. It asks about regular expression patterns, and about the difference between stemming and lemmatization. Note what you miss, then go back to the matching map, such as Tokenization, and read that branch again. Retry the quiz afterwards to see what has stuck.

Read a map to get the outline.
Test yourself with flashcards.
Take a quiz and revisit the weak branches.

Teachers can pick a map or deck to set as a starting point for a class. Choose one resource today and work through it.

Frequently asked questions

Which resource should I open first?

Start with one of the Machine Learning mind maps. They lay out supervised, unsupervised and reinforcement learning with the main methods under each. Once that outline feels familiar, move to the NLU flashcards or the sentiment analysis deck to bring in language processing.

What do the quizzes test?

Unstructured Data Analytics Quizes includes questions on regular expression patterns and on the difference between stemming and lemmatization. There are also quizzes titled Machine Leaning / AI and Module 6 Review. Use them after reading maps to see which topics need another look.

Which levels are these resources for?

Most of the resources are university level, with a small share at a more professional level. The page is aimed at university students and teachers. It suits learners who already have some programming or data background and want to go deeper into neural networks and text analysis.

Are the resources free, and who made them?

Every resource listed here is free to open, study and take, with no account needed. They were made by GoConqr users, not by GoConqr itself. A free account also saves your quiz scores and lets you build your own quizzes, maps, flashcards and notes.

What topics do the mind maps cover?

There are over 20 mind maps. They cover machine learning, DCGAN, variational and sparse autoencoders, word embeddings, Bayesian networks, tokenization, sentiment analysis, text summarising and a hotel review project. Others break down lexical, syntactic and semantic features of text.

What if I cannot find the topic I need?

Check the related maps and decks first, since topics such as tokenization and embeddings appear in several formats. If something is still missing, you can make your own mind map, flashcards or notes to fill the gap and use them for revision.

Deep Learning, AI and Natural Language Processing