- Math and Architectures of Deep Learning! - Jul 15, 2020.
This hands-on book bridges the gap between theory and practice, showing you the math of deep learning algorithms side by side with an implementation in PyTorch. Save 50% with code kdarch50.
- Using Neural Networks to Design Neural Networks: The Definitive Guide to Understand Neural Architecture Search - Oct 14, 2019.
A recent survey outlined the main neural architecture search methods used to automate the design of deep learning systems.
- Activation maps for deep learning models in a few lines of code - Oct 10, 2019.
We illustrate how to show the activation maps of various layers in a deep CNN model with just a couple of lines of code.
- Research Guide for Neural Architecture Search - Oct 4, 2019.
In this guide, we will explore a range of research papers that have sought to solve the challenging task of automating neural network design.
- Training a Machine Learning Engineer - Oct 3, 2019.
There is no clear outline on how to study Machine Learning/Deep Learning due to which many individuals apply all the possible algorithms that they have heard of and hope that one of implemented algorithms work for their problem in hand. Below, I've listed out some of the steps that one should adopt while solving a machine learning problem.
- Multi-Task Learning – ERNIE 2.0: State-of-the-Art NLP Architecture Intuitively Explained - Oct 2, 2019.
The tech giant Baidu unveiled its state-of-the-art NLP architecture ERNIE 2.0 earlier this year, which scored significantly higher than XLNet and BERT on all tasks in the GLUE benchmark. This major breakthrough in NLP takes advantage of a new innovation called “Continual Incremental Multi-Task Learning”.
- Examining the Transformer Architecture: The OpenAI GPT-2 Controversy - Jun 20, 2019.
GPT-2 is a generative model, created by OpenAI, trained on 40GB of Internet to predict the next word. And OpenAI found this model to be SO good that they did not release the fully trained model due to their concerns about malicious applications of the technology.
- Evolving Deep Neural Networks - Jun 18, 2019.
This article reviews how evolutionary algorithms have been proposed and tested as a competitive alternative to address a number of issues related to neural network design.
- Vanguard: Senior AI Architect [Malvern, PA] - Dec 17, 2018.
Vanguard is seeking a Senior AI Architect in Malvern, PA, to work with Business and IT to identify which ideas or problems could potentially be addressed using Artificial Intelligence/Machine Learning, and to conduct experiments and Proofs of Concept for such opportunities.
- Key Takeaways from AI Conference SF, Day 2: AI and Security, Adversarial Examples, Innovation - Oct 30, 2018.
Highlights and key takeaways from selected keynote sessions on day 2 of AI Conference San Francisco 2018.
- Key Takeaways from AI Conference SF, Day 1: Domain Specific Architectures, Emerging China, AI Risks - Oct 29, 2018.
Highlights and key takeaways include Domain Specific Architectures – the next big thing, Emerging China – evolving from copying ideas to true innovation, and Addressing Risks in AI – Security, Privacy, and Ethics.
- Everything You Need to Know About AutoML and Neural Architecture Search - Sep 13, 2018.
So how does it work? How do you use it? What options do you have to harness that power today? Here’s everything you need to know about AutoML and NAS.
- Beginners Ask “How Many Hidden Layers/Neurons to Use in Artificial Neural Networks?” - Jul 16, 2018.
By the end of this article, you could at least get the idea of how these questions are answered and be able to test yourself based on simple examples.
- Foot Locker: Sr Architect – Data Engineering - Apr 3, 2018.
Seeking a candidate to focus on understanding the enterprise data vision and ensuring that various cross-functional teams are aligning their data initiatives to this overall vision.
- Foot Locker: Sr Solutions Architect – Machine Learning and AI Technologies - Mar 30, 2018.
Seeking a candidate to lead the data driven transformation of Foot Locker in partnership with members of the data, CX and infrastructure teams. This role has end-to-end responsibilities for our ML/AI/Cognitive platform - from design, thru technical specification, to delivery.
- Foot Locker: Sr Solutions Architect (Personalization/Adobe Technologies) - Mar 30, 2018.
Seeking a candidate to lead the data driven transformation of Foot Locker in partnership with members of the data, CX and infrastructure teams. This role has end-to-end responsibilities for our Digital Analytics platform - from design, thru technical specification, to delivery.
- Is ReLU After Sigmoid Bad? - Mar 23, 2018.
Recently [we] were analyzing how different activation functions interact among themselves, and we found that using relu after sigmoid in the last two layers worsens the performance of the model.
- How to do Machine Learning Efficiently - Mar 13, 2018.
I now believe that there is an art, or craftsmanship, to structuring machine learning work and none of the math heavy books I tended to binge on seem to mention this.
- KDnuggets™ News 18:n06, Feb 7: 5 Fantastic Practical Machine Learning Resources; 8 Must-Know Neural Network Architectures - Feb 7, 2018.
5 Fantastic Practical Machine Learning Resources; The 8 Neural Network Architectures Machine Learning Researchers Need to Learn; Generalists Dominate Data Science; Avoid Overfitting with Regularization; Understanding Learning Rates and How It Improves Performance in Deep Learning
- The 8 Neural Network Architectures Machine Learning Researchers Need to Learn - Jan 31, 2018.
In this blog post, I want to share the 8 neural network architectures from the course that I believe any machine learning researchers should be familiar with to advance their work.
Pages: 1 2
- Design by Evolution: How to evolve your neural network with AutoML - Jul 20, 2017.
The gist ( tl;dr): Time to evolve! I’m gonna give a basic example (in PyTorch) of using evolutionary algorithms to tune the hyper-parameters of a DNN.
Pages: 1 2 3
- Taxonomy of Methods for Deep Meta Learning - Jun 22, 2017.
This post discusses a variety of contemporary Deep Meta Learning methods, in which meta-data is manipulated to generate simulated architectures. Current meta-learning capabilities involve either support for search for architectures or networks inside networks.
- Game Theory Reveals the Future of Deep Learning - Dec 29, 2016.
This post covers the emergence of Game Theoretic concepts in the design of newer deep learning architectures. Deep learning systems need to be adaptive to imperfect knowledge and coordinating systems, 2 areas with which game theory can help.
- A Reference Architecture for Self-Service Analytics - Nov 10, 2016.
The keys to self-service analytics success are organizational. In addition to a governed self-service architecture, companies need to establish governance committees and gateways, create federated organizations with co-located BI developers, and provide continuous education, training, and support. Learn how to do this in this report.
- Why Do Deep Learning Networks Scale? - Jul 25, 2016.
A discussion of what about deep learning architectures allows them to scale, and addresses some assumptions that often inhibit an understanding of this topic.
- In Deep Learning, Architecture Engineering is the New Feature Engineering - Jul 19, 2016.
A discussion of architecture engineering in deep neural networks, and its relationship with feature engineering.
- Stochastic Depth Networks Accelerate Deep Network Training - Apr 7, 2016.
Read about the presentation and overview of a new deep neural network architectural method, and the response to some strong reaction that it brought about.
- Interview: Stefan Groschupf, Datameer on Why Domain Expertise is More Important than Algorithms - Aug 6, 2015.
We discuss large-scale data architectures in 2020, career path, open source involvement, advice, and more.
- Interview: Thanigai Vellore, Art.com on Why Big Data vs RDBMS is the Wrong Question - Jul 24, 2015.
We discuss success factors with polyglot architectures, Big Data challenges, recommendations for using Big Data technologies, trends, advice, and more.
- Interview: Thanigai Vellore, Art.com on Delivering Contextually Relevant Search Experience - Jul 23, 2015.
We discuss the role of Analytics at Art.com, the polyglot data architecture at Art.com, the use cases for Hadoop, vendor selection, supporting semantic search and experience with Avro.
- Interview: Reiner Kappenberger, HP Security Voltage on Security Checklist for Data Architectures - Jul 10, 2015.
We discuss securing data-at-rest and data-in-motion, security recommendations for data architectures, trends, advice, and more.
- Exclusive Interview: Imran Siddiqi, SAP on Why the Business needs Ambitious Big Data Use Cases - Sep 13, 2014.
We discuss the selection and tracking of use cases, key points for designing a sustainable information architecture, the need for ambitious use cases, SAP's competitive differentiation, and more.
- Interview: Sastry Malladi, StubHub on Designing Big Data Architecture for the Unknown Future - Jul 28, 2014.
We discuss the Big Data architecture at StubHub, important factors in architecture design, hybrid approach of using Big Data along with traditional data warehouses, challenges, importance of meta-data and more.