Deep learning systems are able to learn extremely complex patterns, and they accomplish this by adjusting their weights. How are the weights of a deep neural network adjusted exactly? They are adjusted through a process called backpropagation. Without backpropagation, deep neural networks wouldn’t be able to carry out tasks like recognizing images and interpreting natural language. Understanding how backpropagation works is critical to understanding deep neural networks in general, so let’s delve into backpropagation and see how the process is used to adjust a network’s weights.
Backpropagation can be difficult to understand, and the calculations used to carry out backpropagation can be quite complex. This article will endeavor to give you an intuitive understanding of backpropagation, using little in the way of complex math. However, some discussion of the math behind backpropagation is necessary. Read More
Monthly Archives: January 2020
I (28M) created a deepfake girlfriend and now my parents think we’re getting married
I didn’t want a girlfriend. Don’t get me wrong, I like girls—I just don’t have time for the hassle of dating right now. But I was at a family reunion last year and my parents kept making comments about me still being single: “Oh, he works too hard” and “He’s shy; he just needs to give himself some credit.” My mom was asking my aunts if they could set me up with girls they knew. It was getting to be too much.
So when I got home from the reunion, I signed up for a Worthy account. It was pretty simple: I filled out some information about myself, put in my preferences for gender and age, and in seconds I had an AI-generated virtual girlfriend named “Ivy.” She sent me a text: “Hi, I’m looking forward to getting to know you.” I texted back right away, “Me too, how’s it going?” and my Worthy score in the corner of the screen went up from zero to five. Read More
Six AI Strategies – But Only One Winner
For the last three years we’ve been close observers of exactly what makes a successful AI/ML strategy. In addition to our own observations we’ve been listening closely to VCs and how they describe their internal process for deciding who to fund. It’s remarkable how rapidly and fundamentally this conversation has changed.
The results are in. There is only one demonstrably successful strategy for creating big wins for AI-first companies: platforms. Read More
The US just released 10 principles that it hopes will make AI safer
The principles (with my translation) are:
- Public trust in AI. The government must promote reliable, robust, and trustworthy AI applications.
- Public participation. The public should have a chance to provide feedback in all stages of the rule-making process.
- Scientific integrity and information quality. Policy decisions should be based on science.
- Risk assessment and management. Agencies should decide which risks are and aren’t acceptable.
- Benefits and costs. Agencies should weigh the societal impacts of all proposed regulations.
- Flexibility. Any approach should be able to adapt to rapid changes and updates to AI applications.
- Fairness and nondiscrimination. Agencies should make sure AI systems don’t discriminate illegally.
- Disclosure and transparency. The public will trust AI only if it knows when and how it is being used.
- Safety and security. Agencies should keep all data used by AI systems safe and secure.
- Interagency coordination. Agencies should talk to one another to be consistent and predictable in AI-related policies.
Machine Learning Can’t Handle Long-Term Time-Series Data
More precisely, today’s machine learning (ML) systems cannot infer a fractal structure from time series data.
This may come as a surprise because computers seem like they can understand time series data. After all, aren’t self-driving cars, AlphaStar and recurrent neural networks all evidence that today’s ML can handle time series data?
Nope. Read MOre
What Is The Artificial Intelligence Of Things? When AI Meets IoT
Individually, the Internet of Things (IoT) and Artificial Intelligence (AI) are powerful technologies. When you combine AI and IoT, you get AIoT—the artificial intelligence of things. You can think of internet of things devices as the digital nervous system while artificial intelligence is the brain of a system. Read More
Keeping Top AI Talent in the United States (CSET Report)
Talent is core to U.S. competitiveness in artificial intelligence, and international graduate students are a large source of AI talent for the United States. More than half of the AI workforce in the United States was born abroad, as were around two-thirds of current graduate students in AI-related fields. Tens of thousands of international students get AI-related degrees at U.S. universities every year. Retaining them, and ensuring a steady future talent inflow, is among the most important things the United States can do to address persistent domestic AI work-force shortages and to remain the global leader in AI.
… The good news is that student retention has historically been a core U.S. strength, with well over 80 percent of international U.S.-trained AI PhDs staying in the country, including those from AI competitors such as China.
…The bad news is that two trends are placing this U.S. strength in student retention at risk. Read More
The Next Big Thing in AI/ML is…
“The Next Big Thing in AI/ML is…” as the lead to an article is probably the most overused trope since “once upon a time”. Seriously, just how many ‘next big things’ can there be? Is your incredulity not stretched every time you read that?
It’s tempting to say that writers starting an article in this way should be flogged …except that yours truly did recently start one with “the next most IMPORTANT thing in AI/ML…” Well that’s clearly different isn’t it – almost. Read More
These are the best free Artificial Intelligence educational (2020)
Deep learning is not a beginner-friendly subject — even for experienced software engineers and data scientists.
Deep learning is not a beginner-friendly subject — even for experienced software engineers and data scientists. If you’ve been Googling this subject, you may have been confused by the resources you’ve come across.
To find the best resources, we surveyed engineers on their favorite sources for deep learning, and these are what they recommended.
These educational resources include online courses, in-person courses, books, and videos. All are completely free and designed by leading professors, researchers, and industry professionals like Geoffrey Hinton, Yoshua Bengio, and Sebastian Thrun. Read More
Learning Deep Neural Networks incrementally forever
The hallmark of human intelligence is the capacity to learn. A toddler has comparable aptitudes to reason about space, quantities, or causality than other ape species (source). The difference of our cousins and us is the ability to learn from others.
The recent deep learning hype aims to reach the Artificial General Intelligence (AGI): an AI that would express (supra-)human-like intelligence. Unfortunately current deep learning models are flawed in many ways: one of them is that they are unable to learn continuously as human does through years of schooling, and so on. Read More
Rick's Cafe AI 