Deep Learning is Not Enough: Deep Reasoning is the Answer

An autonomous car has a safety application, but is it good enough to predict whether the car will crash?

Of course, not.

The solution, an urgent need for machine learning models to reason its assertions and clear it to humans.

Artificial intelligence is said to be better than humans at doing multiple things. For example, weather prediction, diagnosis of a disease, or winning a game of chess. If we pen down the list, there are end number of things where AI beat humans, except answering questions that require logical reasoning.

Let’s assume there’s an image of certain shapes and sizes fitted in a single frame with multiple colors. Now you question the system, what is the size of the cylinder that is lying at the left side of the brown metal which is on the left of the big sphere? Perhaps, a six-year-old would be able to answer the question just by looking at the image.

image of cubes and squares
Source: Kaggle

But such questions are still out of hand for traditional deep learning models to understand.

Why you need more than just deep learning?

The models run by deep learning only helps you understand the relationship taking place between input and output. Be it reinforcement learning or supervised learning, the input and the output have been defined for the model to understand. This task works great for generation or classification, however, it doesn’t work well when it comes to making decisions also called abstract reasoning. You need to enable the model to reason.

Example of Abstract Reasoning

example of abstract reasoning
Source: practiceaptitudetests

What is deep reasoning and how do you implement deep reasoning?

Deep reasoning gives you the ability to enable machines that can understand the relationship called implicit (stated) relationship between multiple things.

For instance, all herbivores animals eat plants. The giraffe is an herbivore animal. Over here, the implicit relationship is that all giraffe eats plants, but it was not explicitly (unstated) mentioned. Humans are great when it comes to differentiating the difference between implicit and explicit relationships i.e. relational reasoning. But when it comes to computers it’s a challenge, they need to have strict and explicit rules.

Is there a way we might be able to give computers the ability to reason?

Well, according to DeepMind researchers, the deep learning needs to answer questions with 96 percent accuracy – and this was achieved using three networks namely:

  1. Relation Network (RN): identify how different objects relate to each other

On processing the image, the network can identify the relationship between different objects. For instance, it learns the potential relationship between object pairs like a red cylinder and a blue cube.

  1. Long-Short-Term-Memory Network (LSTM): used to process the question

They understand the sequences clearly because they have a great memory, thus remembering the previous part of the sequence.

  1. Convolutional Neural Network (CNN): to process image

This network identifies every object from an image therefore they can easily identify all the features that are present in the image.

Source: towardsdatascience

Deep reasoning takeaways

  • It allows artificial intelligence to identify the abstract relationship between multiple other different things.
  • This might just be another step that will take us closer to what’s called “artificial general intelligence.
  • Relation networks can be plugged into deep learning models to generate relational reasoning functionalities.

Till then, you can keep training deep learning models to achieve more than 96 percent accuracy.

Start your journey of knowledge with brainstorming box. Our mission is to make learning easier and Interesting than it has ever been. Each day, we curate fascinating topics for those who pursue knowledge with passion.

Starlink Mission: Story of Space Internet

For those of you space geeks out there, you must have seen or heard about the string of satellites floating like bright dots in...

Structure of the black hole- In detail

Black holes are exceptional prediction done by Einstein in the general theory of relativity. Since then, scientists have identified many occurrences...

Neuro-Symbolic AI: Machines to Build Reasoning Power Like Humans

Perhaps you’ve heard about neural networks, software simulations interconnected inside a computer that helps learn things, recognize patterns, and make decisions in the same...

The 3 Essential Types of Quantum Computers And Their Applications

Quantum computing works on quantum mechanics, like superposition and entanglement. This simply means that quantum computers use qubits instead of bits making computers unimaginably...

AI Winter Skepticism: Where We’re Heading?

AI winter! Are we at the tipping point of an AI winter or has it channeled over the years? Rethink Robotics, a Boston-based robotics company founded...

Flowers Growing in Space? How are NASA’s Astronauts Doing It?

Arabidopsis thaliana! This plant became the first full life cycle to happen in space – Salyut 7 during the 80s. Astonishing, overwhelming, or surprised? Well, recently...