Presented at #H2OWorld 2017 in Mountain View, CA. Enjoy the video: https://youtu.be/ZrlJQqNaSMI. Learn more about H2O.ai: https://www.h2o.ai/. Follow @h2oai: https://www.twitter.com/h2oai.
This session was recorded in San Francisco on February 5th, 2019 and can be viewed here: https://youtu.be/VAW2eDht7JA Bio: Krish Swamy is an experienced professional with deep skills in applying analytics and BigData capabilities to challenging business problems and driving customer insights. Krish's analytic experience includes marketing and pricing, credit risk, digital analytics and most recently, big data analytics and data transformation. His key experiences lie in banking and financial services, the digital customer experience domain, with a background in management consulting. Other key skills include influencing organizational change towards a data and analytics driven culture, and building teams of analytics, statisticians and data scientists. Bio: Balaji Gopalakrishnan has over 15 years experience in the Machine Learning and Data Science space. Balaji has led cross functional data science and engineering teams for developing cutting-edge machine learning and cognitive computing capabilities for insurance fraud and underwriting, telematics, multi-asset class risk, scheduling under uncertainty, and others. He is passionate about driving AI adoption in organizations and strongly believes in the power of cross functional collaboration for this purpose.
An overview of why AI and Deep Learning are hot now? Overview f Machine Intelligence startups. What are the key ingredients for AI startup? How can AI startups compete with big tech companies and areas to focus on for differentiation?
This session took place at New York City on November 4th, 2019. Speaker Bio: Chemere is a Senior Data Science Training Specialist for H2O.ai. Chemere has a Master's in Business Administration with focus in Marketing Analytics from the University of North Carolina at Charlotte. She is an experienced data scientist with a diverse background in transformational decision-making in various industries including Banking, Manufacturing, Logistics, and Medical Devices. Chemere joins us from Venus Concept/2two5, where she was the Lead Data Scientist focused on building predictive models with Internet of Things (IoT) data and for a subscription-based marketing product for B2B customers. Prior to that, Chemere worked as a Senior Data Scientist at Wells Fargo Bank focused on various applied predictive analytic solutions. More details about the event can be had here: https://www.eventbrite.com/e/dive-into-h2o-new-york-tickets-76351721053
Numerai is an open, crowd-sourced hedge fund powered by predictions from data scientists around the world. In return, participants are rewarded with weekly payouts in crypto. In this talk, Joe will give an overview of the Numerai tournament based on his own experience. He will then explain how he automates the time-consuming tasks such as testing different modelling strategies, scoring new datasets, submitting predictions to Numerai as well as monitoring model performance with H2O Driverless AI and R.
This slide was presented by Dmitry Baev, Pratap Ramamurthy and Karthik Kannappan at our AWS DevDay in Toronto, Canada on July 17, 2019
1. The document discusses emerging trends in artificial intelligence and machine learning towards a driverless world. Key trends discussed include recommendation engines, facial recognition using deep learning, object and person identification using computer vision, biometrics like fingerprinting, voice assistants in homes and cars, and vehicle-to-vehicle communication technologies. 2. The document also covers applications of AI and machine learning like cognitive IoT, deep learning in healthcare for disease prediction, integrating car telematics with artificial intelligence, and machine learning platforms and techniques. 3. Overall the document provides an overview of the state of artificial intelligence and machine learning technologies and their role in enabling an emerging driverless world.
Technologische mogelijkheden en GDPR, een continue clash? En hoe staat het met de het ethisch (her)gebruik van data? Leer in deze sessie van Rabobank’s Big Data journey en krijg inzicht in: organisatorische keuzes, data Lab technologie visie & data strategie, als enabler en accelerator van digitale innovatie en transformatie.
Jim Spohrer from IBM gave a talk on the future of AI. Some key points: 1) IBM is heavily involved in open source AI through its Cognitive Opentech Group and projects on GitHub. Leaderboards like SQuAD are used to measure progress. 2) The timeline for solving difficult AI problems like commonsense reasoning and learning from experience is 5-10 more years. Job and skills impacts will be felt sooner. 3) Stakeholders at all levels need to participate in and learn about open source AI to help build the future and prepare for changes. Understanding how to rapidly rebuild systems from scratch will be important.
The document discusses Nimbix, a company that provides cloud computing services for high-performance computing (HPC) and artificial intelligence (AI) workloads. It describes Nimbix's history and infrastructure, including partnerships with IBM to provide IBM Power systems and GPUs. The document then explains concepts around AI, different types of AI, and how Nimbix's cloud is well-suited for AI tasks like research, analysis, algorithm development and training.
Artificial Intelligence Beyond Theory & Concepts - Our AI Summer Academy Empowers Silicon Valley School Students to AI Innovation - Free Two Day Event
This presentation was made on June 30th, 2020. Recording of the presentation is available here: https://youtu.be/9LajqAL_CU8 As enterprises “make their own AI”, a new set of challenges emerge. Maintaining reproducibility, traceability, and verifiability of machine learning models, as well as recording experiments, tracking insights, and reproducing results, are key. Collaboration between teams is also necessary as “model factories” are created for enterprise-wide model data science efforts. Additionally, monitoring of models ensures that drift or performance degradation is addressed with either retraining or model updates. Finally, data and model lineage in case of rollbacks or addressing regulatory compliance is necessary. H2O ModelOps delivers centralized catalog and management, deployment, monitoring, collaboration, and administration of machine learning models. In this webinar, we learn how H2O can assist with operationalizing, scaling and managing production deployments. Speaker's Bio: Felix is a part of the Customer Success team in Asia Pacific at H2O.ai. An engineer and an IIM alumni, Felix has held prominent positions in the data science industry.
This session was recorded in San Francisco on February 5th, 2019 and can be viewed here: https://youtu.be/aXPE6IiKRmI The 2018 Brazilian Presidential Elections represented a tangible demonstration of radical change in the way candidates conduct their campaigns, as the shift from traditional media to social media hit the shore of the largest country in the southern hemisphere. Analyzing the political agenda, the broadcast TV-based debates and exchange on social media networks was an NLP feast that The AI Academy reckoned was too good to pass. In this panel, we present the work we conducted , and will show how Driverless AI helped us accelerate our NLP experiments thanks to the recent introduction of advanced text analytics recipes. Bio: Maker/Dreamer/Iconoclast/Chaordic Leader with over 20 years of experience across a number of high-tech industries around the world. Curiosity towards new technologies and the ability to adapt to different cultural and social environments has taken him from a research lab in Italy to a start up in Denmark, to a multinational technology company in Silicon Valley, and ultimately to a leading broadband and video service provider in Brazil. Time and again his career journey has demonstrated his ability to recognize at a very early stage high-potential disruptive ideas and the determination to transform an idea into a real product / service. Over the past seven years, Carmelo cultivated his passion for innovation by leading major technology incubations at a large Telecom operator, supporting the Brazilian startup ecosystem as a Mentor at a startup accelerator and continuously extending his business and technology knowledge through a blend of formal learning & hands-on projects implementations. His focus over the past few years has been on Data Science and Artificial Intelligence, carrying out in-depth technology investigations, product incubations and solutions development. By establishing The AI Academy, Carmelo intends to create and foster a rich environment for the study, research and application of Machine/Deep Learning techniques to real-life use cases, bridging the AI gap between talent and Enterprises - and furthermore elevating Brazil's "AIQ", inserting São Paulo on the world's AI Map.
Read the top five news stories in artificial intelligence and learn how innovations in AI are transforming business across industries like healthcare and finance and how your business can derive tangible benefits by implementing AI the right way.
In this presentation, Parul Pandey, will provide a history and overview of the field of “Automatic Machine Learning” (AutoML), followed by a detailed look inside H2O’s open source AutoML algorithm. H2O AutoML provides an easy-to-use interface which automates data pre-processing, training and tuning a large selection of candidate models (including multiple stacked ensemble models for superior model performance). The result of the AutoML run is a “leaderboard” of H2O models which can be easily exported for use in production. AutoML is available in all H2O interfaces (R, Python, Scala, web GUI) and due to the distributed nature of the H2O platform, can scale to very large datasets. The presentation will end with a demo of H2O AutoML in R and Python, including a handful of code examples to get you started using automatic machine learning on your own projects. Parul's Bio: Parul is a Data Science Evangelist here at H2O.ai. She combines Data Science, evangelism and community in her work. Her emphasis is to spread the information about H2O and Driverless AI to as many people as possible, She is also an active writer and has contributed towards various national and international publications.
Artificial intelligence is becoming a hot topic due to recent advances in hardware capabilities, neural networks research, and technology investments. Deep learning is driving this resurgence by using neural networks with multiple layers to interpret nonlinear relationships in high-dimensional data. Deep learning is delivering improved performance on complex problems and creating value with little domain knowledge required. The presentation provides examples of AI applications in industries like banking, automotive, and healthcare. It also outlines steps to get started with an AI pilot project and developing an AI strategy and roadmap.
These slides were presented at a meetup in Kansas City by Bahador Khaleghi of H2O.ai. More details can be viewed here: https://www.meetup.com/Kansas-City-Artificial-Intelligence-Deep-Learning/events/265662978/
Examples, techniques, and lessons learned building data products over the last 4 years at LinkedIn. Pete Skomoroch is a Principal Data Scientist at LinkedIn where he leads a team focused on building data products leveraging LinkedIn's powerful identity and reputation data. The talk describes some techniques and best practices applied to develop products like LinkedIn Skills & Endorsements. This talk was presented at the SF Data Science Meetup on September 19th, 2013
This document discusses the role of data, algorithms, and people in driving transformation. It emphasizes that code and software are changing the world, and that data ecosystems and alliances will be important going forward. Open source is presented as a way to defend community through code and products. The document also stresses the importance of building ecosystems rather than just products, treating data science as a team sport, and using storytelling in conjunction with data.
The document discusses transformation through data and AI. It provides examples of transformation including from caterpillar to butterfly, engineer to founder, and darkness to light. It also discusses the life cycle of data from data to insight to story to wisdom and how data transforms processes. Throughout the document, it emphasizes that algorithms plus data and people can lead to transformation and that data and AI can enable transformation.
The document discusses several converging technologies and their impact on abundance, connectivity, knowledge, intelligence, and human longevity. It argues that exponential growth in technologies like computing, sensors, networks and AI will lead to a future of ubiquitous connectivity, perfect knowledge access, augmented intelligence, and dramatically increased human healthspans and lifespans approaching 100 years old. Specific examples discussed include the explosion of global internet access through satellite constellations, the connection of trillions of IoT sensors, augmented reality for just-in-time skills and mentoring, and emerging biomedical technologies targeting aging to enable much longer, healthier lives.
Data is the fuel of the connected world, and aspects like value, trust, transparency and ultimately ownership have been a continuous source for debate. As our technical capabilities and our comfort with and within the connected world evolves, so does the conversation about our habits and practices around customer data. As a product strategy and design company that has been leading the industry for more than four decades, I believe that frog is in a good position to reflect forward.
Artificial Intelligence for Business Transformation. - Powered by the open source machine learning software H2O.ai. Contributors welcome at: https://github.com/h2oai - To view videos on H2O open source machine learning software, go to: https://www.youtube.com/user/0xdata
The document discusses the 60th anniversary of CCITT/ITU-T and artificial intelligence. It notes that 10 mobile/cloud companies achieving $4 trillion in market cap and that China's AI market is $337 billion. It discusses how AI is driving unprecedented changes through hyper time compression of innovations and extreme convergence across multiple domains. AI is also helping to track progress on the UN's Sustainable Development Goals. The ITU is partnering with IBM Watson on AI initiatives and standards are being discussed. Overall, the document outlines how AI is massively impacting the economy, society and driving disruption through new technologies.
This document summarizes a presentation given by Vishwanath G Karaveeramath on recent trends in AI technology. The presentation addressed common questions around AI, defined artificial intelligence, and discussed how AI is being used in various fields like customer service, social media, graphic design, and chatbots. While AI can perform some human jobs, it has limitations and cannot fully replace humans. Certain fields like medicine, tourism, transportation, sports, food industry, law making, and business/hospitality are unlikely to be fully automated. In conclusion, AI is best in limited applications and cannot take over humans, but it can create a parallel world amongst us.
AI IS EATING THE WORLD Since the industrial revolution we have seen that we automate every system the can be automated efficiently. Created massive distribution of wealth. With AI and Bots, we are moving from automating “simple” repetitive tasks to autonomous systems that can handle complex and changing situations. It is not a question what verticals will be disrupted, it is a question of when, a few examples…
Tijdens de vierde sessie van de vierdelige reeks Master Minds on Data Science hield Eric van Tol een presentatie over businesscases en verdienmodellen.
Technologies are changing the requirements for industrial parks and collective intelligence systems can help anticipate future changes. As artificial intelligence, computational sciences, and other emerging technologies converge their capabilities will greatly accelerate progress beyond what any single technology can achieve alone based on Moore's law. This will change what is possible and require new thinking about the future of work, economics, and how industrial parks can support tenants through consulting, maker hubs, industrial ecology networks, and collective intelligence systems.
This talk was given to the Tech User Group, Central Oregon on November 15th, 2023. ~~ AI revolutionizes the way we interact with information. It will change the way we work. In this talk, we will introduce the fundamental concepts and the latest research and policies in the field. We will then explore numerous opportunities and societal challenges related to technology adoption, work augmentation and identity. Finally, we will introduce Personal AI and the mission of Kwaai Lab. Kwaai Lab, a non-profit, volunteer-based open-source AI lab, is composed of researchers, architects, developers, and philosophers. Our goal is to design and implement the tools, fundamentals, and policies that empower us all to own our own Personal AI assistants.
THoMers Dennis, Inge, Laetitia, Pieter and Thomas attended Web Summit, the largest tech conference in the world, hosted in Lisbon, Portugal. Web Summit equals 22 conferences connecting different industries, from AutoTech and MoneyConf to SaaS Monster and Talk Robot. The keyword across all conferences? Artificial Intelligence!
The document discusses the emergence of deep learning as the latest development in artificial intelligence. It notes that deep learning saw explosive growth in 2016, with €717M raised for deep learning startups, up from €316M in 2015. Deep learning algorithms have proven able to tackle problems in ways that other AI cannot. The document suggests key factors enabling deep learning's development are increased data availability, greater computing power, and improved algorithms/researchers. It notes that 2017-2018 will be important years to determine if deep learning becomes a mainstream technology or fades, and which companies can achieve significant growth or exits.
The golden age of wearables is upon us. But we should be wary: there is no easy path forward. From smart watches to smart socks to smart door locks, the business models are uncertain and the competition is intense. There are five battlegrounds ahead for companies that want to survive.
These slides are the summary of y presentation on A.I. In Africa: Perspectives and Challenges during the Conference organized by MBCode Consulting Group under the theme: where is Africa on the map of AI?. The goal was to evangelize and raise awareness among the youth about A.I. and how it applies on the continent, and also the necessity to invest time on that direction
APD along with partners IBM and Australia Post, hosted ‘Best of the Next’, an event which brought industry leaders and clients together to discuss innovation in the face of digital disruption, and what businesses can do to capitalise on these trends. The topics discussed by APD’s own Chief Transformation Officer, Inês Almeida and CEO, Scott Player included: • Artificial Intelligence: Hopes and Fears in Perspective • The Impact of 5G and Greater Connectivity • Privacy and security after the Facebook uproar: self-sovereign ID, advertising and Blockchain Guest speakers Tung Nguyen and Cameron Gough from Australia Post presented their latest innovation around Digital ID. For more information visit: http://www.apdgroup.com/bestofthenext/
“AGI should be open source and in the public domain at the service of humanity and the planet.”
Introduces the role of Big Data and AI in the transformation of jobs. It will provide an overview of the skills needed by students if they are seeking for jobs in the area of Big Data and AI.
Jim Spohrer (IBM) gave a presentation at the UCLA BIT Conference on July 19, 2018 about the future of AI. He discussed how AI is currently at the peak of hype but deep learning requires large amounts of data and computing power. He presented a roadmap to solve AI through open technologies, innovation, and service system evolution. Spohrer argued stakeholders should prepare for the AI future by learning skills like coding on platforms like GitHub and competing on AI leaderboards to advance progress.
This document discusses emerging technologies from 2012-2016 and their future implications. It describes how mobile device usage surpassed desktops by 2014, and how messaging apps exceeded social media usage. It also discusses advances in biotechnology like a 16-year-old inventing a low-cost 3D printed bioreactor for growing "mini brains" and conducting disease research. Finally, it outlines developments in computing like IBM and Google expanding access to quantum computers through the cloud.
This document provides an overview of H2O.ai, an AI company that offers products and services to democratize AI. It mentions that H2O products are backed by 10% of the world's top data scientists from Kaggle and that H2O has customers in 7 of the top 10 banks, 4 of the top 10 insurance companies, and top manufacturing companies. It also provides details on H2O's founders, funding, customers, products, and vision to make AI accessible to more organizations.
Here are some key points about benchmarking and evaluating generative AI models like large language models: - Foundation models require large, diverse datasets to be trained on in order to learn broad language skills and knowledge. Fine-tuning can then improve performance on specific tasks. - Popular benchmarks evaluate models on tasks involving things like commonsense reasoning, mathematics, science questions, generating truthful vs false responses, and more. This helps identify model capabilities and limitations. - Custom benchmarks can also be designed using tools like Eval Studio to systematically test models on specific applications or scenarios. Both automated and human evaluations are important. - Leaderboards like HELM aggregate benchmark results to compare how different models perform across a wide range of tests and metrics.
Pritika Mehta, Co-Founder, Butternut.ai H2O Open Source GenAI World SF 2023
The document discusses LLMOps (Large Language Model Operations) compared to traditional MLOps. Some key points: - LLMOps and MLOps face similar challenges across the development lifecycle, but LLMOps requires more GPU resources and integration is faster due to more models in each application. Evaluation is also less clear. - The LLMOps field is around the 5th generation of models, with debates around proprietary vs open source models, and balancing privacy, cost and control. - LLMOps platforms are emerging to provide solutions for tasks like prompting, embedding databases, evaluation, and governance, similar to how MLOps platforms have evolved.
The document discusses optimizing question answering systems called RAG (Retrieve-and-Generate) stacks. It outlines challenges with naive RAG approaches and proposes solutions like improved data representations, advanced retrieval techniques, and fine-tuning large language models. Table stakes optimizations include tuning chunk sizes, prompt engineering, and customizing LLMs. More advanced techniques involve small-to-big retrieval, multi-document agents, embedding fine-tuning, and LLM fine-tuning.
Sandeep Singh, Head of Applied AI Computer Vision, Beans.ai H2O Open Source GenAI World SF 2023 In the modern era of machine learning, leveraging both open-source and closed-source solutions has become paramount for achieving cutting-edge results. This talk delves into the intricacies of seamlessly integrating open-source Large Language Model (LLM) solutions like Vicuna, Falcon, and Llama with industry giants such as ChatGPT and Google's Palm. As the demand for fine-tuned and specialized datasets grows, it is imperative to understand the synergy between these tools. Attendees will gain insights into best practices for building and enriching datasets tailored for fine-tuning tasks, ensuring that their LLM projects are both robust and efficient. Through real-world examples and hands-on demonstrations, this talk will equip attendees with the knowledge to harness the power of both open and closed-source tools in a coherent and effective manner.
Patrick Hall, Professor, AI Risk Management, The George Washington University H2O Open Source GenAI World SF 2023 Language models are incredible engineering breakthroughs but require auditing and risk management before productization. These systems raise concerns about toxicity, transparency and reproducibility, intellectual property licensing and ownership, disinformation and misinformation, supply chains, and more. How can your organization leverage these new tools without taking on undue or unknown risks? While language models and associated risk management are in their infancy, a small number of best practices in governance and risk are starting to emerge. If you have a language model use case in mind, want to understand your risks, and do something about them, this presentation is for you!
Dr. Alexy Khrabrov, Open Source Science Community Director, IBM H2O Open Source GenAI World SF 2023 In this talk, Dr. Alexy Khrabrov, recently elected Chair of the new Generative AI Commons at Linux Foundation for AI & Data, outlines the OSS AI landscape, challenges, and opportunities. With new models and frameworks being unveiled weekly, one thing remains constant: community building and validation of all aspects of AI is key to reliable and responsible AI we can use for business and society needs. Industrial AI is one key area where such community validation can prove invaluable.
The document announces the launch of the H2O GenAI App Store, which provides a collection of applications that make it easier for average users to leverage large language models through custom interfaces for specific tasks like getting gardening advice or feedback on code. The app store is designed to accelerate the development of these GenAI apps using the H2O Wave platform and provides access to H2OGPTE for retrieval augmented generation and language model calls. Developers can also contribute their own apps through the GitHub repository listed.
Megan Kurka, Vice President, Customer Data Scientist, H2O.ai H2O Open Source GenAI World SF 2023 Discover the transformative power of Applied Gen AI. Learn how the H2O team builds customized applications and workflows that integrate capabilities of Gen AI and AutoML specifically designed to address and enhance financial use cases. Explore real world examples, learn best practices, and witness firsthand how our innovative solutions are reshaping the landscape of finance technology.
This document discusses techniques for improving language models (LLMs) discussed in recent papers. It describes building blocks of LLMs like fine-tuning, foundation training, memory, and databases. Specific techniques covered include LIMA which uses 1,000 carefully curated examples, instruction backtranslation to generate question-answer pairs, fine-tuning models on API examples like Gorilla, and reducing false answers through techniques like not agreeing with incorrect user opinions. The goal is to discuss cutting edge tricks to build better LLMs.
Pascal Pfeiffer, Principal Data Scientist, H2O.ai H2O Open Source GenAI World SF 2023 This talk dives into the expansive ecosystem of Large Language Models (LLMs), offering practitioners an insightful guide to various relevant applications, from natural language understanding to creative content generation. While exploring use cases across different industries, it also honestly addresses the current limitations of LLMs and anticipates future advancements.
- Jon McKinney, Director of Research, H2O.ai - Arno Candel, Chief Technology Officer, H2O.ai H2O Open Source GenAI World SF 2023
This document discusses using large language models (LLMs) for text classification tasks. It begins by describing how LLMs are commonly used for text generation and question answering. For classification, models are usually trained supervised on labeled data. The document then explores using LLMs for zero-shot classification without training, and techniques like fine-tuning LLMs on tasks to improve performance. It provides an example of fine-tuning an LLM on a financial sentiment dataset. The document concludes by describing H2O.ai's LLM Studio tool for fine-tuning and a few Kaggle competitions where LLMs achieved success in text classification.
1) Generative AI (GenAI) enables the creation of novel content by learning patterns in unstructured data rather than labeling outputs like traditional AI. 2) Both traditional and generative AI models lack transparency and may contain biases, but generative models can additionally hallucinate or leak private information. 3) To interpret generative models, researchers evaluate accuracy globally by checking for hallucinations or undesirable content, and locally by confirming the quality of individual responses.
Luiz Pizzato, Executive Manager Artificial Intelligence, Commonwealth Bank H2O Open Source GenAI World SF 2023
Machine Learning Model Deployment and Scoring on the Edge with Automatic Machine Learning and Data Flow YouTube Video URL: https://youtu.be/gB0bTH-L6DE Deploying Machine Learning models to the edge can present significant ML/IoT challenges centered around the need for low latency and accurate scoring on minimal resource environments. H2O.ai's Driverless AI AutoML and Cloudera Data Flow work nicely together to solve this challenge. Driverless AI automates the building of accurate Machine Learning models, which are deployed as light footprint and low latency Java or C++ artifacts, also known as a MOJO (Model Optimized). And Cloudera Data Flow leverage Apache NiFi that offers an innovative data flow framework to host MOJOs to make predictions on data moving on the edge.
This presentation was made on June 18, 2020. Video recording of the session can be viewed here: https://youtu.be/YEtDwYSXXJo For many companies, model documentation is a requirement for any model to be used in the business. For other companies, model documentation is part of a data science team’s best practices. Model documentation includes how a model was created, training and test data characteristics, what alternatives were considered, how the model was evaluated, and information on model performance. Collecting and documenting this information can take a data scientist days to complete for each model. The model document needs to be comprehensive and consistent across various projects. The process of creating this documentation is tedious for the data scientist and wasteful for the business because the data scientist could be using that time to build additional models and create more value. Inconsistent or inaccurate model documentation can be an issue for model validation, governance, and regulatory compliance. In this virtual meetup, we will learn how to create comprehensive, high-quality model documentation in minutes that saves time, increases productivity, and improves model governance. Speaker's Bio: Nikhil Shekhar: Nikhil is a Machine Learning Engineer at H2O.ai. He is currently working on our automatic machine learning platform, Driverless AI. He graduated from the University of Buffalo majoring in Artificial Intelligence and is interested in developing scalable machine learning algorithms.
H2O.ai provides open source machine learning platforms and enterprise AI solutions that help companies implement artificial intelligence. It offers tools for data scientists to build models using Python and R and also provides support services to help customers successfully deploy models in production. H2O.ai aims to democratize AI and help companies become AI-driven by leveraging its experts, community knowledge, and world-class technology.
This presentation was made on June 9th, 2020. Video recording of the session can be viewed here: https://youtu.be/OCB9sTUnUug In this meetup with Sanyam Bhutani, Machine Learning Engineer at H2O.ai, he gives a recap of the eight annual ICLR (International Conference on Learning Representations) 2020 - a niche deep learning conference whose focus is to study how to learn representations of data, which is basically what deep learning does. Sanyam goes through a few of his favorite selected papers from this year’s ICLR, note this session may not be able to capture the richness of all papers or allow a detailed discussion. You will be able to find Sanyam in our community slack (https://www.h2o.ai/slack-community/), please feel free to start a discussion with him, if you send a emoji greeting, you’ll find the answers. Following are the papers we will look into: U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty Your classifier is secretly an energy based model and you should treat it like one ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators ALBERT: A Lite BERT for Self-supervised Learning of Language Representations Reformer: The Efficient Transformer Generative Models for Effective ML on Private, Decentralized Datasets Once for All: Train One Network and Specialize it for Efficient Deployment Thieves on Sesame Street! Model Extraction of BERT-based APIs Plug and Play Language Models: A Simple Approach to Controlled Text Generation BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning Real or Not Real, that is the Question