Enabling Sustainable Agriculture: InstaDeep uses Cloud TPU v4
2649
Of your peers have already read this article.
3:30 Minutes
The most insightful time you'll spend today!
You are what you eat. We’ve all been told this, but the truth is what we eat is often more complex than we are – genetically at least. Take a grain of rice. The plant that produces rice has 40,000 to 50,000 genes, double that of humans, yet we know far more about the composition of the human genome than of plant life. We need to close this knowledge gap quickly if we are to answer the urgent challenge of feeding 8 billion people, especially as food security around the globe is likely to worsen with climate change.
For this reason, AI company InstaDeep has teamed up with Google Cloud to train a large AI model with more than 20 billion parameters on a dataset of reference genomes for cereal crops and edible vegetables, using the latest generation of Google’s Tensor Processing Units (Cloud TPU v4), which is particularly suited for training efficiency at scale. Our aim is to improve food security and sustainable agriculture by creating a tool that can analyze and predict plants’ agronomic traits from genomic sequences. This will help identify which genes make some crops more nutritious, more efficient to grow, and more resilient and resistant to pests, disease and drought.
Genomic language models for sustainable agriculture
Ever since farming began, we have been, directly or indirectly, trying to breed better crops with higher yields, better resilience and, if we’re lucky, better taste too. For thousands of years, this was done by trial and error, growing crops year-on-year while trying to identify and retain only the most beneficial traits as they naturally arise from evolutionary mutations. Now that we have access to the genomic sequences of plants, we hope to directly identify beneficial genes and predict the effect of novel mutations.
However, the complexity of plant genomes often makes it difficult to identify which variants are beneficial. Revolutionary advances in machine learning (ML) can help to understand the link between DNA sequences and molecular phenotypes. This means we now have precise and cost-effective prediction methods to help us close the gap between genetic information and observable traits. These predictions can help identify functional variants and accelerate our understanding of which genes link to which traits – so we can make better crop selections.
Moreover, thanks to the vast library of available crop genetic sequences, training large models on hundreds of plant genomes means we can transfer the knowledge from thoroughly-studied species to those that are less understood but important for food production – especially in developing countries. And by doing this digitally, AI can quickly map and annotate the genomes of both common and rare crop variants.
One of the major limitations of traditional ML methods for plant genomics has been they mostly rely on supervised learning techniques. They need labeled data. Such data is scarce and expensive to collect, severely limiting these methods. Recent advances in natural language processing (NLP), such as Transformer architectures and BERT-style training (Bidirectional Encoder Representations from Transformers), allow scientists to train massive language models on raw text data to learn meaningful representations. This unsupervised learning technique changes the game. Once learned, the representations can be leveraged to solve complex regression or classification tasks – even when there is a lack of labeled data.
InstaDeep partners with Google Cloud to train the new generation of AI models for genomics on TPUs
Researchers have demonstrated that large language models can be especially effective in proteomics. To understand how this works, imagine reading amino acids as words and proteins as sentences. The treasure trove of raw genomics data – in sequence form – inspired InstaDeep and Google Cloud to apply similar technologies on nucleotides, this time reading them as words and chunks of genomes as sentences.
Moreover, the representations that the system learned improved in line with the size of the models and datasets, NLP research studies showed. This finding led InstaDeep researchers to train a set of increasingly larger language models on genomics datasets ranging from 1 billion to 20 billion parameters.
- Models of 1 billion and 5 billion parameters were trained on a dataset comprising the reference genomes for several edible plants, including fruit, cereal and vegetables for a total of 75 billion nucleotides.
- The training dataset must increase in the same proportion as the model capacity, recent work has shown. Thus, we created a larger dataset gathering all reference genomes available on the National Center for Biotechnology Information (NCBI) database including human, animal, non-edible plant and bacteria genomes. This dataset, which we used to train a 20-billion-parameter Transformer model, comprised 700 billion tokens, exceeding the size of most datasets typically used for NLP applications, such as the Common Crawl or Wikipedia dataset.
- Both teams announced that the 1 billion-parameter model will be shared with the scientific community to further accelerate plant genomics research.
The compact and meaningful representations of nucleotide sequences learned by these models can be used to tackle molecular phenotype prediction problems. To showcase their ability, we trained a model to predict the gene function and gene ontology (i.e. a gene’s attribute) for different edible plant species.
Early results have demonstrated that this model can predict these characteristics with high accuracy – encouraging us to look deeper at what these models can tell us. Based on these results, we decided to annotate the genomes of three plant species with considerable importance for many developing countries: cassava, sweet potato, and yam. We are working on making these annotations freely available to the scientific community and hope that these will be used to further guide and accelerate new genomic research.
Overcoming scaling challenges with massive models and datasets with Cloud TPUs
The compute requirement for training our 20 billion-parameter model with billions of tokens is massive. While modern accelerators offer impressive peak performance per chip, to utilize this performance often requires tightly coupled hardware and software optimizations. Moreover, maintaining this efficiency when scaling to hundreds of chips presents additional system design challenges. The Cloud TPU’s tightly-coupled hardware and software stack is especially well suited to such challenges. The Cloud TPU software stack is based on the XLA Compiler which offers out-of-the-box optimizations (such as compute and communication overlap) and an easy programming model for expressing parallelism.
We successfully trained our large models for genomics by leveraging Google Tensor Processing Units (TPUv4). Our code is implemented with the JAX framework. JAX provides a functional programming-based approach to express computations as functions that can be easily parallelized using JAX APIs powered by XLA. This helped us to scale from a single host (four chips) configuration to a multi-host configuration without having to tackle any of the system design challenges. The TPU’s cost-effective inter- and intra-communication capabilities led to an almost linear scaling between the number of chips and training time. This allowed us to train the models quickly and efficiently on a grid of 1024 TPUv4 cores (512 chips).
Conclusion
Ultimately, our hope is that the functional characterization of genomic variants predicted by deep learning models will be critical to the next era in agriculture, which will largely depend on genome editing and analysis. We envisage that novel approaches, such as in-silico mutagenesis – the assessment of all possible changes in a genomic region by a computer model – will be invaluable in prioritizing mutations that improve plant fitness and guiding crop improvements. Attempting similar work in wet-lab experiments would be difficult to scale and nearly impossible in nature. By making our current and future annotations available to the research community, we also hope to help democratize breeding technologies so that they can benefit all of global agriculture.
Further Reading
To learn more about the unique features of Cloud TPU v4 hardware and software stack we encourage readers to explore Cloud TPU v4 announcement. To learn more about scaling characteristics, please see this benchmark and finally we recommend reading PJIT Introduction to get started with JAX and SPMD parallelism on Cloud TPU.
This research was made possible thanks to the support of Google’s TPU Research Cloud (TRC) Program which enabled us to use the Cloud TPUv4 chips that were critical to this work.
5163
Of your peers have already watched this video.
24:00 Minutes
The most insightful time you'll spend today!
BK Medical’s Lift and Shift of SAP Environs on Google Cloud Results in Real-time Success
BK Medical is known for designing active imaging systems to help care providers visualize anatomy and provide real-time guidance to aid surgical interventions. After becoming an entity independent of the parent company, Analogic corporation, BK Medical decided to separate its SAP environs from the latter, and move into cloud. After assessing cloud vendors with Managecore, BK Medical chose Google Cloud as its managed service provider that could serve as a single source of truth and also help walk through the lift and shift of SAP ECC systems to the cloud. Watch the video to learn how the migration impacted BK Medical’s goals.
6079
Of your peers have already watched this video.
1:30 Minutes
The most insightful time you'll spend today!
Explore the Innovations and Architecture Powering Spanner and BigQuery
Previously, databases had architectures with tightly coupled storage and compute. This resulted in higher latency, and with faster networks these constraints no longer surface. With Google Cloud’s BigQuery and CloudSpanner, the storage and compute architecture have been separated, allowing for better scalability and availability to address businesses’ high throughput data needs.
Watch the video to understand how these database and analysis products leverage Google’s distributed storage system, in-house custom network hardware and software, internal cluster management system and more!
How Notified Managed to Boost AI-driven, Dynamic Influencer Discovery and Classify its Content Using NLP
3005
Of your peers have already read this article.
2:00 Minutes
The most insightful time you'll spend today!
Notified is a leading communications cloud for events, public relations, and investor relations to drive meaningful insights and outcomes. They provide communications solutions to effectively reach and engage customers, investors, employees, and the media.
One of Notified’s Public Relations solutions is the ‘Media Contact Database’ that allows customers to discover media and influencers in a unique media database powered by AI and human-curated research.
The goal of the initiative is to expand the scope of the AI driven, dynamically discovered influencers, and analyze online news articles using AI/ML technologies to extract entities and classify content. The prior process to extract insights from news articles provided only 30-40% of the desired results, and there were accuracy and stability issues that resulted in a lot of manual intervention.
Journalist Beat
A key outcome of the AI driven process is to identify the ‘Journalist Beat’. A Journalist Beat essentially summarizes the individual’s area of focus such as a sports writer, financial journalist etc.
Three options were evaluated for the AI/ML process to generate the Journalist Beats :
Option 1: Topic ML
Unsupervised ML approach to determine the commonly used terms.
- Pro: Common approach to grouping documents and determine similar text
- Con: Unbounded list of text
Option 2: ML Classification
Build classification models (supervised) to map reference articles to ‘Beats’
- Pro: Aligns to ‘Research Analytics’ existing processes
- Con: Time to build and maintain ML models for hundreds of beats.
Option 3: GCP Context Classification
Leverage GCP’s Natural Language API for initial classification and as input to Notified single model
- Pro: Aligns to ‘Research Analytics’ without building ML models.
Ultimately the GCP Natural Language API solution was chosen because of the speed of execution and a high level of accuracy with the pretrained models. The Notified team was able to launch the product feature within a few weeks, without ever needing to do extensive data collection and train the models.
Here is the high level process that was implemented for Journalist Beats.
Since Notified supports curated media contacts globally, news articles were instantly translated to English using GCP Translation API. GCP Natural Language API’s solution to classify text was used to analyze the translated text and generate the list of content categories.
Solution Architecture
Here is a sample solution architecture for the ‘Discovered Journalist’ process.
Three core principles guided the above architecture – Serverless & Fully Managed, Scalability & Elasticity for flexibility and to optimize costs, API led real-time processing.
In addition to the GCP Natural Language API and Translation API below are a few serverless GCP products that were part of the automated solution:
- BigQuery is Google Cloud’s fully managed, petabyte-scale, and cost-effective analytics data warehouse that lets you run analytics over vast amounts of data in near real time.
- Cloud Run is a fully managed serverless platform that can be used to develop and deploy highly scalable containerized applications.
- Cloud Tasks is a fully managed service that allows you to manage the execution, dispatch, and delivery of a large number of distributed tasks.
The powerful pre-trained models of the Natural Language API provide a comprehensive set of features to apply natural language understanding to applications such as sentiment analysis, entity analysis, entity sentiment analysis, content classification, and syntax analysis.
Notified looks ahead to super-scaling
In an effort to even further improve its best in class ‘Media Contact Database’, Notified looks to super scale the above AI driven Influencer Discovery process to the order of 100+ million news articles per month. It plans to expand the scope of entities extracted from the news articles and provide a news exploration service for its customers by performing intelligent entity-based searches.To watch your markets evolve, see how competitors add AI insights. To actually stay in the market, make AI the main driver of your product road maps. GCP Natural Language API accelerated our ability to adopt AI at scale.
Thomas Squeo, CTO, Notified
Acknowledgments
We’d like to thank our collaborators at Google and Notified for making this blog post possible. Thanks to Arpit Agrawal at MediaAgility for contributing to this blog post.
To learn more about how Google Cloud Natural Language AI can help your enterprise, try out an interactive demo and take the next step, visit the product overview page here.
Master AI Prompt Engineering with 6 Proven Tips
1044
Of your peers have already read this article.
2:30 Minutes
The most insightful time you'll spend today!
As AI-powered tools become increasingly prevalent, prompt engineering is becoming a skill that developers need to master. Large language models (LLMs) and other generative foundation models require contextual, specific, and tailored natural language instructions to generate the desired output. This means that developers need to write prompts that are clear, concise, and informative.
In this blog, we will explore six best practices that will make you a more efficient prompt engineer. By following our advice, you can begin creating more personalized, accurate, and contextually aware applications. So let’s get started!
Tip #1: Know the model’s strengths and weaknesses
As AI models evolve and become more complex, it is essential for developers to comprehend their capabilities and limitations. Understanding these strengths and weaknesses can help you, as a developer, avoid making mistakes and create safer, more reliable applications.
For example, an AI model that is trained to recognize images of blueberries may not be able to recognize images of strawberries. Why? Because the model was only trained on a dataset of blueberry images. If a developer uses this model to build an application that is supposed to recognize both blueberries and strawberries, the application would likely make mistakes, leading to an ineffective outcome, and poor user experience.
It’s important to note that AI models have the ability to be biased. This is due to AI models being trained on data that is collected from the real world, and so it can reflect the inequitable power dynamics inherently rooted in our social hierarchy. If the data that is used to train an AI model is biased, then the model will also be biased. This can lead to problems if the model is used to make decisions that affect people by reinforcing societal biases. Addressing these biases is important to ensure that data is fair, promoting equality, and ensuring the responsibility of AI technology. Prompt engineers should be aware of training limitations or biases so they can craft prompts more effectively and understand what kind of prompting is even possible for a given model.
Tip #2: Be as specific as possible
AI models have the ability to comprehend a variety of prompts. For instance Google’s PaLM 2 can understand natural language prompts, multilingual text, and even programming codes like Python and JavaScript. Although AI models can be very knowledgeable, they are still imperfect, and have the ability to misinterpret prompts that are not specific enough. In order for AI models to navigate ambiguity, it is important to tailor your prompts specifically to your desired outcome.
Let’s say you would like your AI model to generate a recipe for 50 vegan blueberry muffins. If you prompt the model with “what is a recipe for blueberry muffins?”, the model does not know that you need to make 50 muffins. It is thus unlikely to list the larger volume of ingredients you’ll need or include tips to help you more efficiently bake such a large number of muffins. The model can only go off the context that is provided. A more effective prompt would be “I am hosting 50 guests. Generate a recipe for 50 blueberry muffins.” The model is more likely to generate a response that is relevant to your request and meets your specific requirements.
Tip #3: Utilize contextual prompts
Utilize contextual information in your prompts to help the model gain an in-depth understanding of your requests. Contextual prompts can include the specific task you want the model to perform, a replica of the output you’re looking for, or a persona to emulate, from a marketer or engineer to a high school teacher. Defining a tone and perspective for an AI model gives it a blueprint of the tone, style, and focused expertise you’re looking for to improve the quality, relevance, and effectiveness of your output.
In the case of the blueberry muffins, it is important to prompt the model using the context of the situation. The model might need more context than generating a recipe for 50 people. If it needs to be aware that the recipe must be vegan friendly, you might prompt the model by asking it to answer by emulating a skilled vegan chef.
By providing contextual prompts, you can help ensure that your AI interactions are as seamless and efficient as possible. The model will be able to more quickly understand your request and it will be able to generate more accurate and relevant responses.
Tip #4: Provide AI models with examples
When creating prompts for AI models, it is helpful to provide examples. This is because prompts act as instructions for the model, and examples can help the model to understand what you are asking for. Providing a prompt with an example looks something like this: “here are several recipes I like – create a new recipe based on the ones I provided.” The model can now understand the your ability and needs in order to make this pastry,
Tip #5: Experiment with prompts and personas
The way you construct your prompt impacts the model’s output. By creatively exploring different requests, you will soon have an understanding of how the model weighs its answers, and what happens when you interfuse your domain knowledge, expertise, and lived experience with the power of a multi-billion parameter large language model.
Try experimenting with different keywords, sentence structures, and prompt lengths to discover the perfect formula. Allow yourself to step into the shoes of various personas, from work personas such as “product engineer” or “customer service representatives,” to parental figures or celebrities such as your grandmother, a celebrity chef, and explore everything from cooking to coding!
By crafting unique, and innovative, requests replete with your expertise and experience, you can learn which prompts provide you with your ideal output. Further refining your prompts, known as ‘tuning,’ allows the model to have a greater understanding and framework for your next output.
Tip #6: Try chain-of-thought prompting
Chain of thought prompting is a technique for improving the reasoning capabilities of large language models (LLMs). It works by breaking down a complex problem into smaller steps, and then prompting the LLM to provide intermediate reasoning for each step. This helps the LLM to understand the problem more deeply, and to generate more accurate and informative answers. This will help you to understand the answer better and to make sure that the LLM is actually understanding the problem.
Conclusion
Prompt engineering is a skill that all workers, across industries and organizations, will need as AI-powered tools are becoming more prevalent. Remember to incorporate these five essential tips the next time you communicate with an AI model, so you can generate the accurate outputs that you desire. AI will forever continue to develop, constantly refining itself as we use it, so I encourage you to remember that learning, for mind and machine, is a never ending journey. Happy Prompting!
Google Cloud’s Recommendation AI Helps Bazaarvoice with 60 Percent increase in CTR
4496
Of your peers have already read this article.
2:00 Minutes
The most insightful time you'll spend today!
Not long ago, building AI into recommendation engines was a daunting, expensive task that could take years to get off the ground. But as Bazaarvoice has shown, with the help of cloud services, the time from AI investment to business outcomes is shorter than ever.
Bazaarvoice is the leading provider of product reviews and user-generated content (UGC) solutions that help brands and retailers understand and better serve customers. Its 2019 acquisition of Influenster.com, a community of consumer reviewers 6.5 million strong, expanded the Bazaarvoice portfolio with a platform where consumers can share their candid opinions — and share they have, over 54 million times.
After the acquisition, Bazaarvoice expanded the site’s product diversity by 53%, to more than 5.4 million unique products. To keep user engagement high, Influenster must be seen as both a source of trusted, transparent reviews and a place for customers to discover useful, relevant products for the first time. By introducing shoppers to new products Influenster not only provides value to customers but also helps brands collect consumer insights.
Influenster started out as a place where people gathered to share their honest thoughts on beauty products but quickly expanded to nearly every category, from Art to Wearables. Because of the much smaller scope, the site started and flourished under a rules-based recommendation engine. However, as Influenster expanded its scope under Bazaarvoice, a more robust recommendation system became necessary. In its earliest days, Influenster was successful because of the human perspective it offered: For every product there was a litany of reviews and images that made users feel as if they were getting an endorsement on a product from a friend.
The Bazaarvoice engineering team asked themselves how they could keep that same feeling of personalization with an ever-growing catalog of items and categories. They needed recommendations that could scale with the site, rather than requiring more rules be constructed each time a new product category was introduced. They also needed to ensure the Influenster experience would remain performant even towards unknown members.
Bazaarvoice tested out several recommendation engines, benchmarking each against their current rules-based system. In the end they decided on Google Cloud’s Recommendations AI because of its transparent billing, ease of integration and setup, and naturally, its proven results.
Transparent Billing
“Part of what the engineers loved was they knew exactly what it was going to cost as it scaled” says Nick Shiftan, SVP, Content Acquisition Services Product Unit for Influenster. The goal was to build once and innovate rather than leave a wake of technical debt only to be tackled when costs grew unexpectedly out of control. Google Cloud’s straightforward and pay-as-you-go billing allowed them to anticipate how costs would grow as user interactions did and plan accordingly.
Ease of integration
“I’m positively surprised how Google packed such a complex system in a very easy-to-use API” remarks Eralp Bayraktar, the Software Engineering team lead overseeing the project. Because the original team was made of just one full-time engineer the ease of integration became an even more critical feature. Not only does Recommendations AI pull from years of suggestion expertise in Google Search and YouTube, but in combination with Ad’s Merchant Center, it also creates a streamlined process for importing product metadata. From there, creating a model becomes a matter of picking the preferred recommendation type and then the business objective to optimize for. Once the model is created and the API integrated into the website, the code is already deployed at the global scale: There are no further architectural considerations to ensure recommendations are available to users worldwide. For Bazaarvoice, this meant going from ideation to production in one month.
Proven Results
“We have used it for product recommendations and off-loaded our DB-tiring business logic to Recommendations AI, which resulted in overall faster response times and much better recommendations as proven by our A/B tests,” Eralp continues.
Bazaarvoice began by A/B testing Recommendations AI against their rules-based system. Early on in the experimental phase they noticed a clear and consistent 60% increase in the click-through rate over their original recommendation system.
Even more impressive was the performance on Unknown Members. For every person that signs up for an account on Influenster.com there are many other visitors that come to the website and leave without fully registering. This is typically referred to as the “cold start” problem in the industry — how do you figure out what to recommend to those people without their history, behavior, or preferences? Recommendations AI gives you the option to input and train on unknown users, and by providing metadata on products, it can provide high-quality suggestions to registered members and first-time users alike.
With a mind to the future, Eralp concludes his thoughts on Bazaarvoice’s experience: “It enables discovery by adding an adjustable percentage of cross-category products [for] healthier [traffic distribution] across all our catalog. We are investing in data science and having the Recommendations AI as the baseline is a good challenge for us to thrive.”
To learn more about Recommendations AI and how it can help your organization thrive, check out our recently published 4 part guide which kicks off with an overview on “How to get better retail recommendations with Recommendations AI.” This series also covers data ingestion, modeling, as well as serving predictions & evaluating Recommendations AI. You can also easily get started with our Quickstart Guide.
More Relevant Stories for Your Company
Document AI
Most business transactions begin, involve, or end with a document. But working with documents can be tricky, as leaders across industries seeking digital transformation can attest to. These enterprises face similar challenges as they seek to extract information from documents. The process can be costly, time consuming, and prone to
Google Migration and BigQuery Brings PedidosYa Closer towards its Goal of Becoming Data-driven
Editor’s note: PedidosYa is the market leader for online food ordering in Latin America, serving 15 markets and over 400 cities. It’s also one of the largest brands within the German multinational company Delivery Hero SE. With over 20 million app downloads, PedidosYa provides the best online delivery experience through
Google Introduces ML-based Predictive Autoscaling to Forecast Capacity and Match Scaling Demands
At Google Cloud, we believe you get most benefits from the cloud when you scale infrastructure based on changing demand. Compute Engine allows you to configure autoscaling to save costs during periods of low demand, and add capacity to support peak loads. When you use a managed instance group (MIG), you can have an autoscaler
Google Cloud’s Firebase Realtime Database and BigQuery AllowsCastbox to Ramp Up Customer Experience
Demand for spoken audio content such as podcasts remains robust despite the proliferation of video services and other entertainment options for consumers. Shibin Li, Co-founder of Castbox, credits growth of the global podcast platform to the following: speed and availability, market-leading features, the proliferation of smart devices to deliver audio content,
