Final Exam: ML Architect will test your knowledge and application of the topics presented throughout the ML Architect track of the Skillsoft Aspire ML Programmer to ML Architect Journey.
describe approaches for architecting and building machine learning pipelines to implement scalable machine learning systems
describe approaches of implementing reinforcement learning
describe checklists for machine learning projects that are to be prepared and adopted by project managers
describe computational graphs
describe dynamic programming, policy evaluation, policy iteration, value iteration, and characteristics of Bellman equation
describe TensorFlow extended and TFX pipeline components
describe the concept of deep reinforcement learning and its application in the areas of robotics, finance, and healthcare
describe the Machine Learning workflow steps
describe the multi-armed bandit problem and different approaches of solving this problem
describe the prominent statistical classification models and compare generative classifiers with discriminative classifiers
describe the role of recurrent neural network
describe the various architectures of recurrent neural network that can be used in modelling natural language processing
describe what neural networks are and their main components
evaluate and score the performance of your neural network in Keras
identify and work with both types of models available in Keras
identify features of Deep Learning that can improve performance
identify the challenges and patterns associated with deploying deep learning solutions in the enterprise
identify the rules that should be applied when using feature engineering to pull the right features into applications
implement generative adversarial network Discriminator and Generator using Python and Keras and build Discriminator for training model
install the Markov Decision Policy toolbox and implement the Discounted Markov Decision Process using the policy iteration algorithm
list the best practices that should be adopted to build robust machine learning systems, with focus on the evaluation approach
list the various phases of machine learning workflow that can be used to achieve key milestones of machine learning projects
make regression classifications using Keras
prepare your data in Keras by defining your input and target tensors
recall features of commonly used Keras layers and when to use them
recall reinforcement learning algorithms and their features
recall the approach of using deep learning-based frameworks to model NLP tasks and audio data analysis
recall the best practices that should be adopted to build robust machine learning systems
recall the concept of deep learning
recall the concept of deep learning and the approach of using deep learning-based frameworks to model NLP tasks and audio data analysis
recall the data workflows that are used to develop machine learning models
recognize features of commonly used Keras layers and when to use them
recognize how ELM tends to produce better scalability, generalization performance, and faster learning than traditional support vector machine
recognize key features of Decision Trees and Random Forests
recognize key features of Linear and Logistic regressions
recognize reinforcement learning terms that are used in building reinforcement learning workflows
recognize the data workflows that are used to develop machine learning models
recognize the role of reward and discount factors in reinforcement learning
troubleshoot deep learning errors by tuning the model
understand how a proposed new scene-centric database is successfully used for learning deep features for
understand how convolutional neural networks may be utilized as a powerful class of models for image recognition
understand how initializing a network with transferred features may boost generalization performance
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
understand the efforts being undertaken to reduce overfitting using the dropout technique
understand the proposed learning framework for deep residual learning that improves training of networks that are significantly deeper than traditional neural networks
use case studies to analyze the impacts of adopting best practices for deep learning
use deep convolutional autoencoder with Keras and Python
use Keras to make regression classifications
use Python and related data analysis libraries to perform exploratory data analysis
use Python to perform exploratory data analysis
working with deep learning autoencoders
working with Deep Learning frameworks
working with Machine Learning algorithms to build Deep Learning networks
work with reinforcement learning agents using Keras and OpenAI Gym