Final Exam: DL Programmer will test your knowledge and application of the topics presented throughout the DL Programmer track of the Skillsoft Aspire ML Programmer to ML Architect Journey.
build a recurrent neural network using PyTorch and Google Colab
build deep learning language models using Keras
build neural networks using PyTorch
calculate Loss function and score using Python
compare the supervised and unsupervised learning methods of artificial neural networks
define and classify Activation functions and provide a comparative analysis with the pros and cons of the different types of Activation functions
define and illustrate the use of learning rates to optimize deep learning
define multilayer perceptrons and illustrate the algorithmic difference from single layer perceptrons
define semantic segmentation and its implementation using Texton Forest and random-based classifier
define the concept of the Edge Detection method and list the common algorithms that are used for Edge detection
define the concepts of variance, covariance and random vectors
demonstrate how to build a Convolutional Neural network for Image classification using Python
demonstrate how to select hyperparameters and tune for dense networks using Hyperas
demonstrate how to test multiple models and select the right model using Scikit-learn
demonstrate the implementation of differentiation and integration in R
describe functions in calculus
describe gradient descent and list its prominent variants
describe ResNet layers and blocks
describe sequence modeling as it pertains to language models
describe shared parameters and spatial in a convolutional neural network (CNN)
describe the approach of creating Deep learning network models along with the steps involved in optimizing the networks
describe the concept of Scaling data and list the prominent data scaling methods
describe the iterative workflow for Machine learning problems with focus on essential measures and evaluation protocols
describe the purpose of a training function in an artificial neural network
describe the regularization techniques used in deep neural network
describe the temporal and heterogeneous approaches of optimizing predictions
describe vanishing gradient problem implementation approaches
develop Convolutional Neural network models from the scratch for Object Photo classification using Python and Keras
distinguish been input, output, and hidden layers in a neural network
identify and illustrate the use of learning rates to optimize deep learning
identify the different types of learning rules that can be applied in neural networks
identify the need for Activation layer in Convolutional Neural networks and compare the prominent Activation functions for Deep Neural networks
implement backpropagation using Python to train artificial neural networks
implement calculus, derivatives, and integrals using Python
implement convolutional neural networks (CNNs) using PyTorch
implement long short-term memory using TensorFlow
implement recurrent neural network using Python and TensorFlow
implement the artificial neural network training process using Python
list activation mechanisms used in the implementation of neural networks
list features and characteristics of gated recurrent units (GRUs)
list neural network algorithms that can be used to solve complex problems across domains
list the essential clustering techniques that can be applied on artificial neural network
recall the algorithms that can be used to train neural networks
recall the approaches of identifying overfitting scenarios and preventing overfitting using Regularization techniques
recall the essential Hyperparameters that are applied on Convolutional networks for optimization and model refinement
recall the prominent Optimizer algorithms along with their properties that can be applied for optimization
recognize the differences between the non-linear activation functions
recognize the different types of neural network computational models
recognize the importance of linear algebra in machine learning
recognize the involvement of Maths in Convolutional Neural networks and recall the essential rules that are applied on Filters and Channel detection
recognize the limitations of Sigmoid and Tanh and describe how they can be resolved using ReLU along with the significant benefits afforded by ReLU when applied in Convolutional networks
recognize the Machine learning problems that we can address using Hyperparameters along with the various Hyperparameter tuning methods and the problems associated with Hyperparameter optimization
recognize the need for Activation layer in Convolutional Neural networks and compare the prominent Activation functions for Deep Neural networks
recognize the need for gradient optimization in neural networks
recognize the role of Pooling layer in Convolutional networks along with the various operations and functions that we can apply on the layer
recognize the various approaches of improving the performance of Machine learning using data, algorithm, algorithm tuning and Ensembles
specify approaches that can be used to implement predictions with neural networks
use backpropagation and Keras to implement multi-layer perceptron or neural net
work with Hyperparameters using Keras and TensorFlow to derive optimized Convolutional network models