Research Topics in ML & DL

Machine Learning    |    Intermediate
  • 13 videos | 41m 41s
  • Includes Assessment
  • Earns a Badge
Rating 4.3 of 16 users Rating 4.3 of 16 users (16)
This course explores research being done in machine learning and deep learning. Topics covered include neural networks and deep neural networks. First, learners examine how to prevent neural networks from overfitting. You will explore research on multilabel learning algorithms, multilabel classification, and multiple-output classifications, which are variants of the standard classification problem. Then examine deep learning algorithms, the enhanced performance of deeper neural networks that are more adept at automatic feature extraction. Next, ut facial alignment, regression tree ensembles, and deep features for scene recognition. Review ELM (Extreme Learning Machine), and how it is used to perform regression and multiclass classification.

WHAT YOU WILL LEARN

  • Understand the efforts being undertaken to reduce overfitting using the dropout technique
    Understand leading edge multi-label learning algorithms
    Understand the proposed learning framework for deep residual learning that improves training of networks that are significantly deeper than traditional neural networks
    Understand how initializing a network with transferred features may boost generalization performance
    Understand how convolutional neural networks may be utilized as a powerful class of models for image recognition
    Understand the dataset that advances state-of-the-art object recognition by considering the context within the question of scene understanding
  • Understand the proposed framework for estimating generative models via an adversarial process that successfully estimates the probability that a sample came from training data rather than a generative model
    Understand how optimal nearest neighbor algorithms perform compared to traditional nearest neighbor algorithms
    Understand how an ensemble of regression trees may successfully estimate facial landmark positions while delivering real-time performance and high quality predictions
    Understand how a proposed new scene-centric database is successfully used for learning deep features for scene recognition
    Recognize how elm tends to produce better scalability, generalization performance, and faster learning than traditional support vector machine
    Understand the trending research topics in ml and dl

IN THIS COURSE

  • 2m 31s
  • 2m 51s
    Upon completion of this video, you will be able to understand the efforts being undertaken to reduce overfitting using the dropout technique. FREE ACCESS
  • Locked
    3.  Multi-Label Learning Algorithms
    3m 56s
    After completing this video, you will be able to understand advanced multi-label learning algorithms. FREE ACCESS
  • Locked
    4.  Deep Residual Learning for Image Recognition
    3m 8s
    Upon completion of this video, you will be able to understand the proposed learning framework for deep residual learning. This framework improves training of networks that are significantly deeper than traditional neural networks. FREE ACCESS
  • Locked
    5.  Transferable Features in Deep Neural Networks
    2m 46s
    After completing this video, you will be able to understand how initializing a network with transferred features may improve generalization performance. FREE ACCESS
  • Locked
    6.  Large-Scale Video Classification
    3m 19s
    After completing this video, you will be able to understand how convolutional neural networks can be used as a powerful class of models for image recognition. FREE ACCESS
  • Locked
    7.  Common Objects in Context
    3m 11s
    After completing this video, you will be able to understand the dataset that advances state-of-the-art object recognition by considering the context within the question of scene understanding. FREE ACCESS
  • Locked
    8.  Generative Adversarial Nets
    3m 19s
    Upon completion of this video, you will be able to understand the proposed framework for estimating generative models. The framework uses an adversarial process to estimate the probability that a sample came from training data rather than a generative model. FREE ACCESS
  • Locked
    9.  Scalable Nearest Neighbor Algorithms
    2m 50s
    After completing this video, you will be able to understand how optimal nearest neighbor algorithms perform compared to traditional nearest neighbor algorithms. FREE ACCESS
  • Locked
    10.  Face Alignment with Ensemble of Regression Trees
    2m 4s
    Upon completion of this video, you will be able to understand how an ensemble of regression trees may successfully estimate facial landmark positions while delivering real-time performance and high quality predictions. FREE ACCESS
  • Locked
    11.  Learning Deep Features for Scene Recognition
    3m 30s
    After completing this video, you will be able to understand how a proposed new scene-centric database is used for learning deep features for scene recognition. FREE ACCESS
  • Locked
    12.  Extreme Learning Machine (ELM)
    2m 54s
    Upon completion of this video, you will be able to recognize how ELM tends to produce better scalability, generalization performance, and faster learning than traditional support vector machines. FREE ACCESS
  • Locked
    13.  Exercise: Recognize Research Topics in ML and DL
    5m 24s
    Upon completion of this video, you will be able to understand the trending research topics in machine learning and deep learning. FREE ACCESS

EARN A DIGITAL BADGE WHEN YOU COMPLETE THIS COURSE

Skillsoft is providing you the opportunity to earn a digital badge upon successful completion on some of our courses, which can be shared on any social network or business platform.

Digital badges are yours to keep, forever.

PEOPLE WHO VIEWED THIS ALSO VIEWED THESE

Rating 4.5 of 217 users Rating 4.5 of 217 users (217)
Rating 4.1 of 17 users Rating 4.1 of 17 users (17)
Rating 4.5 of 8 users Rating 4.5 of 8 users (8)