To be more precise, the renewed interest in deep learning is largely due to the success of convolutional neural networks (CNNs), a neural network structure that is especially good at dealing with visual data.

Hinton, who attended the conference with Yann LeCun and Yoshua Bengio, with whom he constitutes the Turin Award–winning “godfathers of deep learning” trio, spoke about the limits of CNNs as well as capsule networks, his masterplan for the next breakthrough in AI.

Early work in computer vision involved the use of symbolic artificial intelligence, software in which every single rule must be specified by human programmers.

“But they’re very different from human perception.”.

Our visual system can recognize objects from different angles, against different backgrounds, and under different lighting conditions.

When objects are partially obscured by other objects or colored in eccentric ways, our vision system uses cues and other pieces of knowledge to fill in the missing information and reason about what we’re seeing.

In fact, ImageNet, which is currently the go-to benchmark for evaluating computer vision systems, has proven to be flawed.

This is acceptable for the human vision system, which can easily generalize its knowledge.

But CNNs need detailed examples of the cases they need to handle, and they don’t have the creativity of the human mind.

But data augmentation won’t cover corner cases that CNNs and other neural networks can’t handle, such as an upturned chair, or a crumpled t-shirt lying on a bed.

From the points raised above, it is obvious that CNNs recognize objects in a way that is very different from humans.

The internal representations that CNNs develop of objects are also very different from that of the biological neural network of the human brain.

“I can take an image and a tiny bit of noise and CNNs will recognize it as something completely different and I can hardly see that it’s changed.

That seems really bizarre and I take that as evidence that CNNs are actually using very different information from us to recognize images,” Hinton said in his keynote speech at the AAAI Conference.

Adversarial examples can cause neural networks to misclassify images while appearing unchanged to the human eye.

But when it’s the computer vision system of a self-driving car missing a stop sign, an evil hacker bypassing a facial recognition security system, or Google Photos tagging humans as gorillas, then you have a problem.

Therefore, as long as our computer vision systems work in ways that are fundamentally different from human vision, they will be unpredictable and unreliable, unless they’re supported by complementary technologies such as lidar and radar mapping.

Another problem that Geoffrey Hinton pointed to in his AAAI keynote speech is that convolutional neural networks can’t understand images in terms of objects and their parts.

Also missing from CNNs are coordinate frames, a fundamental component of human vision.

One very handy approach to solving computer vision, Hinton argued in his speech at the AAAI Conference, is to do inverse graphics.

3D computer graphics models are composed of hierarchies of objects.

Each object has a transformation matrix that defines its translation, rotation, and scale in comparison to its parent.

The transformation matrix of the top object in each hierarchy defines its coordinates and orientation relative to the world origin.

Each of these objects have their own transformation matrix that define their location and orientation in comparison to the parent matrix (center of the car).

The world coordinates of the front-left wheel can be obtained by multiplying its transformation matrix by that of its parent.

Capsule networks, Hinton’s ambitious new project, try to do inverse computer graphics.

But if Hinton and his colleagues succeed to make them work, we will be much closer to replicating the human vision