Assinar

Vamos dar uma enqudrada: o que AI pode ou não pode, de fato, fazer por nossa indústria?

Buscar
Meio e Mensagem – Marketing, Mídia e Comunicação

Vamos dar uma enqudrada: o que AI pode ou não pode, de fato, fazer por nossa indústria?

Buscar
Publicidade

Blog do Pyr

Vamos dar uma enqudrada: o que AI pode ou não pode, de fato, fazer por nossa indústria?


2 de junho de 2018 - 14h33

“#AI can help humans expand their abilities in three ways. They can:

  1. amplify our cognitive strengths
  2. interact with customers & employees to free us for higher-level tasks
  3. embody human skills to extend our physical capabilities.”

 

Enviado do meu iPhone

 

Por Carmela Borst (*)

Você já ouviu falar sobre Ke Jie? Ele foi considerado o melhor jogador humano do antigo jogo de tabuleiro chinês Go. Recentemente, porém, foi derrotado por um jogador virtual conhecido como AlphaGo, desenvolvido pelo grupo de pesquisa DeepMind AI da Alphabet. Enquanto isso, em outro canto do mundo, mais precisamente na Suíça, pesquisadores da Penn State University e da Écola Polytechinique Fédérale de Lausanne, usavam conceitos de reconhecimento facial para treinar um computador, a fim de que ele reconhecesse doenças de plantas. O objetivo final, era dar a qualquer pessoa com um smartphone em mãos as mesmas habilidades que um especialista. Fantástico, não? O potencial de aplicações de inteligência artificial como essas é vasto; e as pessoas já começaram a se familiarizar com apps transacionais em seu dia a dia, seja uma interação com a Siri para buscar um restaurante, ou no momento em que paramos para perguntar para Alexa ou Google Home quanto tempo levaremos para chegar ao aeroporto. No mundo B2B, esses apps também se proliferam rapidamente: um exemplo são os chat bots que servem de gateways em sistemas corporativos, como ERP ou Human Capital Management (HCM), e utilizam AI para automatizar tarefas por meio de funções de voz ou chats. Eles podem atuar em funções simples como pedir a um sistema do HCM para inserir uma solicitação de férias; ou tarefas mais avançadas, como entender o histórico de compras do cliente nos últimos 30 dias.Você pode argumentar, com razão, que os exemplos acima não são inteligência artificial de verdade, mas sim uma forma trivial de aprendizado de máquina. Mas o que você não pode discordar, é que essa é apenas a ponta de um grande iceberg.

Pensando e não apenas aprendendo

As tecnologias de inteligência artifical que usamos hoje são, na verdade, bastante limitadas. A tendência é que a próxima geração de sistemas crie novos canais de conhecimento por conta própria. É o que chamamos de inteligência artificial cognitiva, onde os sistemas são capazes de agir com base em aprendizado e raciocínio, fazendo deduções e ampliando seus conhecimentos para que possam fornecer informações, detectar e evitar possíveis problemas, identificar padrões de dados e muito mais.

Com a AI cognitiva, o sistema de gestão de uma empresa que gerencia grandes frotas, pode prever problemas, solicitar peças, agendar a manutenção e executar testes de qualidade para garantir que o equipamento esteja no padrão. No âmbito da saúde, por sua vez, é possível utilizar apps de radiologia baseados em nuvem para reconhecer e identificar resultados normais, permitindo aos radiologias se concentrarem nos diagnósticos que mostrem potenciais anormalidades. Já na área industrial, um fabricante de produtos químicos pode utilizar a AI cognitiva para monitorar as emissões de CO2.

Áreas a observar

Todo mundo que aposta em inteligência artificial quer saber onde estão as maiores oportunidades. Embora as previsões nesse estágio ainda sejam um pouco tênues, existem algumas áreas que a maioria dos especialistas concorda que possuam um potencial significativo.

  • Big Data + AI + visualização de dados e controle de voz – O mundo dos negócios está repleto de dados, mas a AI tem o potencial de levar o uso de big data para a estratosfera. Combinando capacidade de processamento com capacidades de aprendizagem cognitiva, a AI poderá identificar rapidamente padrões em dados que seriam difíceis ou impossíveis para os humanos verem de forma independente. E quando os humanos puderem acessar essas informações via controle de voz ou com fácil entendimento e manipulação de visualizações de dados, seu valor cresce exponencialmente.
  • Asset Management – Essa é uma área em que a IoT já tem um impacto positivo significativo. As informações dos sensores que monitoram tudo, permite que as empresas evitem problemas e aumentem o retorno de seus investimentos. Outras fontes de dados – como relatórios de drones sendo usados para inspeções – estão tornando a informação ainda mais acessível e reduzindo a necessidade de intervenção humana. Acrescente AI cognitiva a essa mistura e você terá o potencial de eliminar em grande parte os seres humanos de um processo que antes era demorado e altamente manual. Imagine um mundo com equipamentos que são virtualmente “auto mantenedores”.
  • Produtividade – Aqui AI pode ter maior impacto. O conceito é: quando as máquinas podem ser usadas para automatizar tarefas rotineiras, os humanos podem dedicar mais tempo ao trabalho que importa.

(*)  Carmela Borst, Diretora Sênior de Marketing para América Latina.

Strategic #AI (@Strat_AI)
19/06/2018 20:26

Maximizing Value from #AI

bit.ly/2t9v85A

#Algorithms #Analytics #ArtificialIntelligence #BigData #BusinessIntelligence #Data #DataMining #DataScience #DeepLearning #MachineLearning #PredictiveAnalytics #Python pic.twitter.com/RDUnqbo2cT

Baixe o aplicativo do Twitter

 

Enviado do meu iPhone

 

http://www.mckinsey.com/business-functions/mckinsey-analytics/our-insights/what-ai-can-and-cant-do-yet-for-your-business?cid=eml-web

Enviado do meu iPhone

 

Enviado do meu iPhone

Início da mensagem encaminhada:

De: “David Kiron, MIT SMR” <smr-noreply@sloan.mit.edu>
Data: 19 de junho de 2018 17:01:01 BRT
Para: <pmarcondes@grupomm.com.br>
Assunto: New AI Articles for Pyr
Responder A: <smr-news@mit.edu>

Human-Computer ‘Superminds’ Are Redefining the Future of Work

Artificial Intelligence for Business Leaders  |  June 2018

 

How Human-Computer ‘Superminds’ Are Redefining the Future of Work

 

 

Virtually all human achievements require the work of groups of people, not just lone individuals. What’s new now is that machines can increasingly participate in the intellectual, as well as the physical, activities of these groups. See how the combination of people and machines will be able to create superminds that are smarter than any groups or individuals our planet has ever known.

 

Read the new article now »

 

Quantitative Intuition: Making Smarter Decisions With Imperfect Information

Data overload? Information is essential to making intelligent business decisions, but more often than not, it overwhelms us in today’s data-rich environment. Learn a systematic framework to make smarter, better-informed decisions during this three-day program.

Learn More »

ADVERTISEMENT

 

NEW IN AI

 

Wait-and-See Could Be a Costly AI Strategy

Sometimes waiting can be a winning strategy, but that outcome depends on the intensity of competition. In the case of AI, you might need to embrace the technology now in order to reinvent how you do business.

 

UPCOMING WEBINAR

 

How Big Data and AI are Driving Business Innovation in 2018

 

Wednesday, June 27
11:00 a.m. EDT / 8:00 a.m. PDT

Join Randy Bean, CEO of New Vantage Ventures and author of “How Big Data and AI Are Driving Business Innovation in 2018,” as he discusses the findings from the 2018 study of Fortune 1000 companies and shares his thoughts on the current and future starts of big data and AI implementation. You will learn why you should have a combined short-term/long-term strategy for big data and AI and how “innovating around the edges” can help you achieve success.

 

Reserve your spot now »

 

If you’re unable to attend live, still register! We’ll send you the on-demand recording after the webinar.

 

8 Keys to Applying AI in Cross-Legacy & Multi-Enterprise Networks

Artificial intelligence can offer a huge benefit to complex organizations and their supply networks, but only if based on solid fundamentals. In this paper, you will learn how AI can be leveraged across disparate, legacy and multi-enterprise systems.

Learn More »

ADVERTISEMENT

 

FROM THE ARCHIVES

 

The Jobs That Artificial Intelligence Will Create

As artificial intelligence systems become ever more sophisticated, another wave of job displacement will almost certainly occur. But here’s what we’ve been overlooking: Many new jobs will also be created – jobs that look nothing like those that exist today.

 

 

CONNECT WITH US

 

ABOUT US             ADVERTISE             STORE             CONTACT US
Share this Mailing:
Manage your preferences | Opt out using TrueRemove®
Got this as a forward? Sign up to receive our future emails. | View this email online.
MIT Sloan Management Review, One Main St., 9th floor, E90-9200
Cambridge, MA | 02142 United States
This email was sent to pmarcondes@grupomm.com.br.
To continue receiving our emails, add us to your address book.

Singularity Hub

How Artificial Intelligence Could Help Us Live Longer

 

Peter H. Diamandis, MD

3 days ago

 

What if we could generate novel molecules to target any disease, overnight, ready for clinical trials?

 

Imagine leveraging machine learning to accomplish with 50 people what the pharmaceutical industry can barely do with an army of 5,000.

 

It’s a multibillion-dollar opportunity that can help billions.

 

The worldwide pharmaceutical market, one of the slowest monolithic industries to adapt, surpassed $1.1 trillion in 2016.

 

In 2018, the top 10 pharmaceutical companies alone are projected to generate over $355 billion in revenue.

 

At the same time, it currently costs more than $2.5 billion (sometimes up to $12 billion) and takes over 10 years to bring a new drug to market. Nine out of 10 drugs entering Phase I clinical trials will never reach patients.

 

As the population ages, we don’t have time to rely on this slow, costly production rate. Some 12 percent of the world population will be 65 or older by 2030, and “diseases of aging” like Alzheimer’s will pose increasingly greater challenges to society.

 

But a world of pharmaceutical abundance is already emerging.

 

As artificial intelligence converges with massive datasets in everything from gene expression to blood tests, novel drug discovery is about to get >100X cheaper, faster, and more intelligently targeted.

 

One of the hottest startups I know in this area is Insilico Medicine.

 

Leveraging AI in its end-to-end drug pipeline, Insilico Medicine is extending healthy longevity through drug discovery and aging research.

 

Their comprehensive drug discovery engine uses millions of samples and multiple data types to a) discover signatures of disease and b) identify the most promising targets for billions of molecules. These molecules either already exist or can be generated de novo with the desired set of parameters.

 

Insilico’s CEO Dr. Alex Zhavoronkov recently joined me on an Abundance Digital webinar to discuss the future of longevity research.

 

Just this week, Insilico announced the completion of a strategic round of funding led by WuXi AppTec’s Corporate Venture Fund, with participation from Pavilion Capital, Juvenescence, and my venture fund BOLD Capital Partners.

 

What they’re doing is extraordinary, and it’s an excellent lens through which to view converging exponential technologies.

 

Case Study: Leveraging AI for Drug Discovery

 

You’ve likely heard of deep neural nets: multilayered networks of artificial neurons, able to ‘learn’ from massive amounts of data and essentially program themselves.

 

Build upon deep neural nets, and you get generative adversarial networks (GANs), the revolutionary technology that underpins Insilico’s drug discovery pipeline.

 

What are GANs?

 

By pitting two deep neural nets against each other (“adversarial”), GANs enable the imagination and creation of entirely new things (“generative”).

 

Developed by Google Brain in 2014, GANs have been used to output almost photographically accurate pictures from textual descriptions (as seen below).

 

 

Source: Reed et al., 2016

Insilico and its researchers are the first in the world to use GANs to generate molecules.

 

“The GAN technique is essentially an adversarial game between two deep neural networks,” as Alex explains.

 

While one generates meaningful noise in response to input, the other evaluates the generator’s output. Both networks thereby learn to generate increasingly perfect output.

 

In Insilico’s case, that output consists of perfected molecules. Generating novel molecular structures for diseases both with and without known targets, Insilico is pursuing drug discovery in aging, cancer, fibrosis, Parkinson’s Disease, Alzheimer’s Disease, ALS, diabetes, and many others. Once rolled out, the implications would be profound.

 

Alex’s ultimate goal is to develop a fully-automated Health as a Service (HaaS) / Longevity as a Service (LaaS) engine. Once plugged into the services of companies from Alibaba to Alphabet, such an engine would enable personalized solutions for online users, helping them prevent diseases and maintain optimal health.

 

But what does this tangibly look like?

 

Insilico’s End-to-End Pipeline

 

First, Insilico leverages AI—in the form of GANs—to identify targets (as seen in the first stage of their pipeline below). To do this, Insilico uses gene expression data from both healthy tissue samples and those affected by disease. (Targets are the cellular or molecular structures involved in a given pathology that drugs are intended to act on.)

 

 

Source: Insilico Medicine via Medium

Within this first pipeline stage, Insilico can identify targets, reconstruct entire disease pathways and understand the regulatory mechanisms that result in aging-related diseases.

 

This alone enables breakthroughs for healthcare and medical research. But it doesn’t stop there.

 

After understanding the underlying mechanisms and causality involved in aging, Insilico uses GANs to ‘imagine’ novel molecular structures. With reinforcement learning, Insilico’s system lets you generate a molecule with any of up to 20 different properties to hit a specified target.

 

This means that we can now identify targets like never before, and then generate custom molecules de novo such that they hit those specific targets.

 

At scale, this would also involve designing drugs with minimized side effects, a pursuit already being worked on by Insilico scientist Polina Mamoshina in collaboration with Oxford University’s Computational Cardiovascular Team.

 

One of Insilico’s newest initiatives—to complete the trifecta, if you will—involves predicting the outcomes of clinical trials. While still in the early stages of development, accurate clinical trial predictors would enable researchers to identify ideal pre-clinical candidates.

 

That’s a 10X improvement from today’s state of affairs.

 

Currently, over 90 percent of molecules discovered through traditional techniques and tested in mice end up failing in human clinical trials. Accurate clinical trial predictors would result in an unprecedented cutting of cost, time, and overhead in drug testing.

 

The 6 D’s of Drug Discovery

 

The digitization and dematerialization of drug discovery has already happened.

 

Thanks to converging breakthroughs in machine learning, drug discovery and molecular biology, companies like Insilico can now do with 50 people what the pharmaceutical industry can barely do with an army of 5,000.

 

As computing power improves, we’ll be able to bring novel therapies to market at lightning speeds, at much lower cost, and with no requirement for massive infrastructure and investments. These therapies will demonetize and democratize as a result.

 

Add to this anticipated breakthroughs in quantum computing, and we’ll soon witness an explosion in the number of molecules that can be tested (with much higher accuracy).

 

Finally, AI enables us to produce sophisticated, multi-target drugs. “Currently, the pharma model in general is very simplistic. You have one target and one disease—but usually a disease is not one target, it is many targets,” Alex has explained.

 

Final Thoughts

 

Inefficient, slow-to-innovate, and risk-averse industries will all be disrupted in the years ahead. Big Pharma is an area worth watching right now, no matter your industry.

 

Converging technologies will soon enable extraordinary strides in longevity and disease prevention, with companies like Insilico leading the charge.

 

Fueled by massive datasets, skyrocketing computational power, quantum computing, blockchain-enabled patient access, cognitive surplus capabilities and remarkable innovations in AI, the future of human health and longevity is truly worth getting excited about.

 

Rejuvenational biotechnology will be commercially available sooner than you think. When I asked Alex for his own projection, he set the timeline at “maybe 20 years—that’s a reasonable horizon for tangible rejuvenational biotechnology.”

 

Alex’s prediction may even be conservative.

 

My friend Ray Kurzweil often discusses the concept of “longevity escape velocity”—the point at which, for every year that you’re alive, science is able to extend your life for more than a year.

 

With a record-breaking prediction accuracy of 86 percent, Ray predicts “It’s likely just another 10 to 12 years before the general public will hit longevity escape velocity.”

 

How might you use an extra 20 or more healthy years in your life? What impact would you be able to make?

 

Image Credit: Jackie Niam / Shutterstock.com

 

Categories: Experts

Tags: Artificial Intelligence, Convergence, Longevity Related Posts

 

Leading With Purpose: How to Turn Your Mission Into a Movement Jun 21, 2018

 

How DeepMind’s Latest AI Hints at Machines That Think More Like Us Jun 19, 2018

 

The More People With Purpose, the Better the World Will Be Jun 15, 2018

 

Pioneering Stem Cell Trial Seeks to Cure Babies Before Birth Jun 13, 2018

 

The Biggest New Laws to Regulate Tech Giants—and Why They Matter Jun 06, 2018

 

Singularity Hub

 

Powered by WordPress

Back to top

 

 

Enviado do meu iPhone

 

 

Publicidade

Compartilhe

Veja também