Hands-on Machine Learning with Scikit-learn and TensorFlow 2

In this video, we will learn what machine learning is.

   •  Learn the concepts of a machine learning pipeline

   •  Learn the types of ML

In this video, we will learn how to load, visualize, and work with datasets.

   •  Understand what ridge regression is

   •  Compare NumPy and scikit-learn

In this video, we will learn about overfitting and regularization.

   •  Learn how to avoid overfitting through regularization

   •  Learn how regularization can impact and simplify a model

In this video, we will learn about probability and review statistics.

   •  Learn Bayes rule

   •  Understand expectation, variances, and co-variances

   •  Learn cross-validation

In this video, we will learn about probability distribution and metrics.

   •  Learn about decision theory

   •  Learn about classification metrics

In this video, we will learn how we can inspect a dataset, and apply KNN classification and regression.

   •  Inspect a dataset using pandas statistical metrics

   •  Use the k-nearest neighbors model

   •  Optimize hyper parameters using cross validation

In this video, we will learn how to use logistic regression and train it with gradient descent optimization.

   •  Understand what Logistic regression is and how it works

   •  Regularize logistic regression and train it

   •  Learn how gradient descent optimization works

In this video, we will learn how to use Naïve Bayes model and its variations and when they are valid.

   •  Understand what Gaussian Naïve Bayes does

   •  Know when to use multinomial Naïve Bayes

   •  Know when to use Bernoulli Naïve Bayes

In this video, we will learn what a Support Vector Machine is, how to train one, variants, and the kernel trick.

   •  Understand what a Support Vector Machine is

   •  Create a non-linear SVM with the kernel trick

   •  Use SVM for regression

In this video, we will learn how decision trees work, visualize them, and use the models in practice for classification and regression.

   •  Use a decision tree for classification

   •  Use a decision tree for regression

   •  Get practical tips and how they work

In this video, we will learn get an overview of averaging methods and boosting methods ensemble methods.

   •  Combine multiple models with a voting classifier

   •  Use random forests

   •  Use boosting, AdaBoost, and gradient tree boosting

In this video, we will learn how to perform unsupervised learning clustering with K-Means, hierarchal clustering, and the various clustering performance evaluation metrics.

   •  Understand what unsupervised learning is and K-Means clustering

   •  Use the various clustering performance evaluation metrics

   •  Perform hierarchal clustering with agglomerative clustering

In this video, we will learn how to perform connectivity and density clustering, with affinity propagation, Birch, Mean shift, Spectral clustering, DBSCAN, and OPTICS.

   •  Use connectivity clustering and affinity propagation

   •  Use Birch, Mean shift, and spectral clustering

   •  Use DBSCAN and OPTICS

In this video, we will learn how to use Gaussian Mixture Models, components, and expectation maximization.

   •  Learn what Gaussian Mixture models are

   •  Select the number of gaussians

   •  Use expectation maximization for GMMs

In this video, we will learn how to use variational Bayesian Gaussian Mixture models, their advantages, and disadvantages, and the Dirichlet process.

   •  Understand what variational Bayesian Gaussian Mixture models are

   •  Learn the advantages and disadvantages in practice

   •  Use the Dirichlet process

In this video, we will learn how to use Singular Value Decomposition in practice, Principal Component Analysis, incremental and kernel PCA, Dictionary Learning, and Generating Dictionary Learning.

   •  Understand what Singular Value Decomposition is and how to use it

   •  Use Principal Component Analysis in practice

   •  Use dictionary learning and generative dictionary learning

In this video, we will learn how to use factor analysis, Independent Component Analysis, non-negative matrix factorization, and the Latent Dirichlet allocation.

   •  Use factor analysis and separating signals with Independent Component Analysis

   •  Use non-negative matrix factorization

   •  Use Latent Dirichlet allocation

In this video, we will learn what Novelty and Outlier detection are, and what outlier detection methods are, and how to use Novelty detection.

   •  Learn what Novelty and Outlier detection are

   •  Learn the methods for detecting outliers

   •  Detect novelties

In this video, we will learn how to detect outliers, variations of Outlier detection, Elliptic, Isolation forest, and detecting with local outlier factor.

   •  Understand how to detect Outliers

   •  Use variations of Outlier detection, Elliptic, and Isolation Forest

   •  Detect with local outlier factor

In this video, we will learn what manifold learning is and why should we care. See what an Isomap is, Locally-linear embedding (LLE), Modified locally-linear embedding (MLLE), Hessian locally-linear embedding (HLLE), Spectral embedding, and Local tangent space alignment (LTSA) are, and how to use them.

   •  Learn what manifold learning is and why it is important

   •  Use Isomap, Locally-linear embeddings, and its variants

   •  Use spectral embedding and local tangent space alignment

In this video, we will learn how to use Multi-dimensional scaling (MDS), T-distributed stochastic neighbor embedding (t-SNE), and practical tips on how to use Manifolds.

   •  Use Multi-dimensional scaling (MDS)

   •  Use T-distributed stochastic neighbor embedding (t-SNE) in practice

   •  Get practical tips on how to use perform Manifold learning

In this video, we will learn how to estimate density with histograms and kernel density estimation.

   •  Create and use histograms for density estimation

   •  Learn what kernel density estimation is

   •  Use kernel density estimation

In this video, we will learn what Boltzmann machines are, Restricted Boltzmann machine (RBM), and how to use them in practice.

   •  Understand What Boltzmann machines are

   •  Learn What Restricted Boltzmann machines (RBM) are

   •  Model and parametrize a Restricted Boltzmann machines

In this video, we will get an overview of TensorFlow 2.0, including Tensors, eager execution, and how to visualize a graph and how automatic differentiation works.

   •  Learn the different types of Tensors

   •  Learn how to visualize a TensorFlow graph

   •  Learn how automatic differentiation works

In this video, we will learn automatic differentiation with the Gradient Tape and how to implement our own model (Ridge Regression) using the Gradient Tape.

   •  Use automatic differentiation using the Gradient Tape

   •  Implement our own Ridge Regression model using the Gradient Tape

   •  Train our custom model

In this video, we will learn about Artificial Neural Networks, activation functions, creating our own Neural Network from scratch in TensorFlow 2.0, equivalent in Keras, and introduction to working with Keras.

   •  Learn what Artificial Neural Networks are

   •  Create our own Neural Network from scratch in TensorFlow 2.0

   •  Create a Neural Network in Keras

In this video, we will learn about TensorFlow 2.0 dataset object, custom models in Keras using the functional API overview, and multiple Keras models from the same graph.

   •  Use the TensorFlow 2.0 dataset object

In this video, we will learn how to use multi output and input models, non-linear networks, sharing layers, re-using nodes, custom layers, custom models, and Keras callbacks.

   •  Use multi output and input models

   •  Share layers and reuse nodes

   •  Create custom layers, models, and Keras callbacks

In this video, we will learn how many of neurons to use, identifying and preventing overfitting, regularization, with Maxnorm, Dropout, and data pre-processing.

   •  Understand how many neurons to use, identifying, and preventing overfitting

   •  Regularize with Maxnorn, dropout, and correct weight initialization

   •  Learn how to pick the right Gradient Descent method

In this video, we will learn how to perform regression with Keras, EarlyStopping callback, Transfer learning overview, Transfer learning with frozen layers, Transfer learning with fine-tuning pre-trained layers.

   •  Train efficiently with EarlyStopping

   •  Learn how to use Transfer learning

   •  Fine-tune a network with Transfer learning

In this video, we will learn get an overview of TensorFlow estimators, estimator setup and training, TensorBoard overview, TensorBoard callback, and example with TensorBoard.

   •  Learn how to use TensorFlow estimators

   •  Learn how to use TensorBoard

In this video, we will learn about Convolutional Neural Networks (ConvNets), architecture overview, and the Convolutional NN layer.

   •  Learn what Convolutional Neural Networks (ConvNets) are

   •  Implement ConvNets in practice

   •  Use the Convolutional NN layer

In this video, we will learn about the pooling layer, ConvNet architecture, ConvNet case studies, and ConvNets in Keras.

   •  Learn the pooling layer

   •  Look at ConvNet case studies

   •  Use ConvNets in Keras

In this video, we will learn about image classification, improving with Data Augmentation, ImageDataGenerator class in TensorFlow, and Dropout with ConvNets.

   •  Learn how to classify images

   •  Improve performance by augmenting our dataset

   •  Use dropout in convnets

In this video, we will get an overview of Autoencoders, Autoencoder architecture, Convolutional Autoencoders, and Deconvolutional layers in Keras.

   •  Implement an autoencoder

   •  Use a convolutional autoencoder

   •  Use the Deconvolutional layer in Keras

In this video, we will learn to use denoising autoencoders, variational autoencoders, and interpolating the VAEs latent space.

   •  Create a denoising autoencoder

   •  Use a variational autoencoder

   •  Interpolate the VAEs latent space

In this video, we will learn about Generative Adversarial Networks overview, theory and custom loss function.

   •  Learn how Generative Adversarial Networks work

   •  Learn about the GAN loss function

   •  Train a GAN

In this video, we will learn about Semantic Segmentation, U-Net model (Using Skip layers), and Transfer learning for image segmentation.

   •  Get an overview of semantic segmentation

   •  Learn about U-Net Model (Using Skip layers)

   •  Use Transfer learning for image segmentation

In this video, we will learn about Neural Style Transfer (NST) theory, Fast Transfer Style using TensorFlow-Hub, NST model, and improving with total variation loss.

   •  Learn about the Neural Style Transfer (NST) theory

   •  Perform Fast Transfer Style using TensorFlow-Hub

   •  Train our own NST model

In this video, we will get an overview of Natural Language Processing, word embeddings, Keras embedding layer, loading a pre-trained word embedding layer, and what embeddings represent.

   •  Learn how to use word embeddings with the Keras embedding layer

   •  Load a pre-trained word embedding layer

   •  Understand what embeddings represent

In this video, we will work with text data, tokenization, N-grams, complete text pipeline for classification example, and use a vocabulary in a pipeline.

   •  Learn how to tokenize text

   •  Create N-grams

   •  Use a vocabulary in a text pipeline

In this video, we will learn about Recurrent Neural Network (RNN) overview, building RNN from scratch in NumPy, using Rolled and Un-Rolled RNNs, Long short-term memory (LSTM) RNN overview, and Gated Recurrent Unit (GRU) RNN overview.

   •  Learn the variants of a Recurrent Neural Network (RNN) and implement our own in NumPy

   •  Understand how a Long short-term memory network (LSTM) works

   •  Learn how a Gated Recurrent Unit (GRU) works

In this video, we will learn about Bidirectional RNN wrapper, stacking RNNs, dropout with RNNs, and we will also look at an example on a Sentiment Classification text problem using RNNs.

   •  Use the Bidirectional RNN wrapper

   •  Explore stack and dropout with RNNs

   •  Perform sentiment classification

In this video, we will learn about time series forecasting data pre-processing, forecasting univariate time series, forecasting baseline, and RNN for univariate and multi-variate forecasting.

   •  Learn how to preprocess time series data into a dataset

   •  Construct a time series prediction baseline

   •  Train a RNN for univariate and multi variate forecasting

In this video, we will learn about multi-step time series forecasting, 1D ConvNets for sequences, combining CNNs and RNNs, and WaveNet CNN variant.

   •  Learn forecasting multi-step time series

   •  Understand what and how to use 1D ConvNets for time series

   •  Combine (WaveNet) ConvNets and RNNs for forecasting

In this video, we will learn about language models overview, vectorize characters, and sequence pre-processing.

   •  Learn language models are

   •  Understand how we can vectorize characters

   •  Process data into sequences

In this video, we will learn about LSTM character language model, sampling from the language model, training a language model, generating text, and advanced training.

   •  Train a LSTM character language model

   •  Sample from a language model

   •  Generate text from the language model

In this video, we will learn about Sequence to Sequence, Machine Translation, and Process input and output sequences for Seq2Seq models.

   •  Learn what Sequence to Sequence (Seq2Seq) problems are

   •  Get an overview of Machine Translation

   •  Process inputs and outputs for Seq2Seq models

In this video, we will learn about Seq2Seq with attention overview, Training Seq2Seq and Visualizing attention.

   •  Improve Seq2Seq with attention

   •  Perform Custom training of Seq2Seq with attention

   •  Visualize attention plots

In this video, we will learn about Transformer overview, Transformer in Keras as a chatbot, multi-head attention, and positional encoding.

   •  Learn about a Transformer and create one in Keras

   •  Create multi-head attention

   •  Create positional encodings

In this video, we will learn about Transformer Encoder and Decoder, Transformer custom loss and learning rate, model case studies, and fine tuning a pre-trained BERT model for classification.

   •  Create Transformer Encoder and Decoder

   •  Understand custom loss and learning rate scheduler

   •  Fine tune a pre-trained BERT model for classification

In this video, we will cover the structure of RL and categories, with simple Markov decision process examples.

   •  Learn how to define reinforcement learning

   •  Categorize different RL paradigms

In this video, we will train a deep Q-Network using TensorFlow TF-Agents.

   •  Learn how to use TF-Agents

   •  Train a deep Q-Network in TF-Agents

In this video, we will look at the best practices at how to set up TF-Agents, environments, policies, drivers, replay buffers, networks, check points and policy saver.

   •  Create a custom environment

   •  Create a custom Policy

   •  Learn the best practices to use TF-Agents

In this video, we will learn what and how to use value based methods (DQN), and policy based methods (PPO).

   •  Learn how to use value based methods (DQN)

   •  Learn how to use policy based methods (PPO)

In this video, we will learn how to use exploration techniques and the uncertainty in RL (Categorical DQN).

   •  Get an overview of exploration techniques

   •  Learn how to use uncertainty in RL (Categorical DQN)

In this video, we will learn about Imitation learning with GAIL and case study implementation of AlphaZero.

   •  Perform Imitation learning with GAIL

   •  Look at a case study implementation of AlphaZero