Final Exam: ML Architect

WHAT YOU WILL LEARN

• 

  Use keras to make regression classifications
  

  implement generative adversarial network discriminator and generator using python and keras and build discriminator for training model
  

  understand the efforts being undertaken to reduce overfitting using the dropout technique
  

  prepare your data in keras by defining your input and target tensors
  

  understand the proposed learning framework for deep residual learning that improves training of networks that are significantly deeper than traditional neural networks
  

  describe the concept of deep reinforcement learning and its application in the areas of robotics, finance, and healthcare
  

  recognize features of commonly used keras layers and when to use them
  

  evaluate and score the performance of your neural network in keras
  

  compile the model in keras
  

  describe what neural networks are and their main components
  

  use deep convolutional autoencoder with keras and python
  

  identify features of deep learning that can improve performance
  

  recognize key features of decision trees and random forests
  

  recall the concept of deep learning
  

  recognize key features of linear and logistic regressions
  

  apply a linear regression with python
  

  recall the best practices that should be adopted to build robust machine learning systems
  

  identify the challenges and patterns associated with deploying deep learning solutions in the enterprise
  

  recall the concept of deep learning and the approach of using deep learning-based frameworks to model nlp tasks and audio data analysis
  

  use python to perform exploratory data analysis
  

  describe computational graphs
  

  recognize reinforcement learning terms that are used in building reinforcement learning workflows
  

  describe the multi-armed bandit problem and different approaches of solving this problem
  

  install the markov decision policy toolbox and implement the discounted markov decision process using the policy iteration algorithm
  

  apply hierarchical clustering with python
  

  work with reinforcement learning agents using keras and openai gym
  

  troubleshoot deep learning errors by tuning the model
  

  recall the data workflows that are used to develop machine learning models
  

  recall reinforcement learning algorithms and their features
  

  understand how convolutional neural networks may be utilized as a powerful class of models for image recognition
• 

  understand how a proposed new scene-centric database is successfully used for learning deep features for
  

  describe the various architectures of recurrent neural network that can be used in modelling natural language processing
  

  list the best practices that should be adopted to build robust machine learning systems, with focus on the evaluation approach
  

  describe checklists for machine learning projects that are to be prepared and adopted by project managers
  

  describe the prominent statistical classification models and compare generative classifiers with discriminative classifiers
  

  working with machine learning algorithms to build deep learning networks
  

  recognize the data workflows that are used to develop machine learning models
  

  recognize how elm tends to produce better scalability, generalization performance, and faster learning than traditional support vector machine
  

  compare deep learning platforms and frameworks
  

  understand how initializing a network with transferred features may boost generalization performance
  

  use case studies to analyze the impacts of adopting best practices for deep learning
  

  list the various phases of machine learning workflow that can be used to achieve key milestones of machine learning projects
  

  working with deep learning frameworks
  

  recall features of commonly used keras layers and when to use them
  

  recall the approach of using deep learning-based frameworks to model nlp tasks and audio data analysis
  

  recognize the role of reward and discount factors in reinforcement learning
  

  use python and related data analysis libraries to perform exploratory data analysis
  

  working with deep learning autoencoders
  

  describe approaches for architecting and building machine learning pipelines to implement scalable machine learning systems
  

  identify and work with both types of models available in keras
  

  identify the rules that should be applied when using feature engineering to pull the right features into applications
  

  understand leading edge multi-label learning algorithms
  

  understand the dataset that advances state-of-the-art object recognition by considering the context within the question of scene understanding
  

  describe approaches of implementing reinforcement learning
  

  describe tensorflow extended and tfx pipeline components
  

  describe dynamic programming, policy evaluation, policy iteration, value iteration, and characteristics of bellman equation
  

  describe the role of recurrent neural network
  

  make regression classifications using keras
  

  describe the machine learning workflow steps