#### Computers and artificial intelligence continue to usher in major changes in the way people shop. It is relatively easy to train a robot’s brain to create a shopping list, but what about ensuring that the robotic shopper can easily tell the difference between the thousands of products in the store?

Purdue University researchers and experts in brain-inspired computing think part of the answer may be found in magnets. The researchers have developed a process to use magnetics with brain-like networks to program and teach devices such as personal robots, self-driving cars and drones to better generalize about different objects.

“Our stochastic neural networks try to mimic certain activities of the human brain and compute through a connection of neurons and synapses,” said Kaushik Roy, Purdue’s Edward G. Tiedemann Jr. Distinguished Professor of Electrical and Computer Engineering. “This allows the computer brain to not only store information but also to generalize well about objects and then make inferences to perform better at distinguishing between objects.”

Roy presented the technology during the annual German Physical Sciences Conference earlier this month in Germany. The work also appeared in the Frontiers in Neuroscience.

The switching dynamics of a nano-magnet are similar to the electrical dynamics of neurons. Magnetic tunnel junction devices show switching behavior, which is stochastic in nature.

The stochastic switching behavior is representative of a sigmoid switching behavior of a neuron. Such magnetic tunnel junctions can be also used to store synaptic weights.

The Purdue group proposed a new stochastic training algorithm for synapses using spike timing dependent plasticity (STDP), termed Stochastic-STDP, which has been experimentally observed in the rat’s hippocampus. The inherent stochastic behavior of the magnet was used to switch the magnetization states stochastically based on the proposed algorithm for learning different object representations.

The trained synaptic weights, encoded deterministically in the magnetization state of the nano-magnets, are then used during inference. Advantageously, use of high-energy barrier magnets (30-40KT where K is the Boltzmann constant and T is the operating temperature) not only allows compact stochastic primitives, but also enables the same device to be used as a stable memory element meeting the data retention requirement. However, the barrier height of the nano-magnets used to perform sigmoid-like neuronal computations can be lowered to 20KT for higher energy efficiency.

“The big advantage with the magnet technology we have developed is that it is very energy-efficient,” said Roy, who leads Purdue’s Center for Brain-inspired Computing Enabling Autonomous Intelligence. “We have created a simpler network that represents the neurons and synapses while compressing the amount of memory and energy needed to perform functions similar to brain computations.”

Roy said the brain-like networks have other uses in solving difficult problems as well, including combinatorial optimization problems such as the traveling salesman problem and graph coloring. The proposed stochastic devices can act as “natural annealer”, helping the algorithms move out of local minimas.

Learn more: A magnetic personality, maybe not. But magnets can help AI get closer to the efficiency of the human brain

##### The Latest on: Stochastic neural networks

*via Google News*

##### The Latest on: Stochastic neural networks

- Binary Classification Using PyTorch: Model Accuracyon November 24, 2020 at 12:37 pm
Next, the demo creates a 4-(8-8)-1 deep neural network. Then the demo prepares training by setting up a loss function (binary cross entropy), a training optimizer function (stochastic gradient descent ...

- Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learningon November 23, 2020 at 11:49 am
Differentiating pseudoprogression from true tumor progression has become a significant challenge in follow-up of diffuse infiltrating gliomas, particularly high grade, which leads to a potential ...

- Designing spontaneous behavioral switching via chaotic itinerancyon November 11, 2020 at 10:03 pm
The properties of CI vary among previous studies, and some classes of CI present interesting features that are difficult to characterize using the stochastic processes. Tsuda et al. (9), for example, ...

- Stochastic Computation applied to the design of Error Correcting Decoderson November 8, 2020 at 4:00 pm
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference ... [96] B. Brown and H. Card. “Stochastic neural computation I: Computational elements,” IEEE Trans. on Computers, 50(9 ...

- Binary Classification Using PyTorch: Trainingon November 4, 2020 at 11:46 am
Next, the demo creates a 4-(8-8)-1 deep neural network. Then the demo prepares training by setting up a loss function (binary cross entropy), a training optimizer function (stochastic gradient descent ...

- Watch Cincinnati vs. SMU: How to Live Stream, TV channel, start timeon October 24, 2020 at 12:45 pm
Understanding methods like stochastic gradient descent might ... taking you from absolute zero to a deep understanding of how neural networks work. To keep things simple, the aim is not to cover ...

- Dr Hua-Liang Weion August 14, 2020 at 3:11 pm
Artificial neural networks (ANN), radial basis function networks (RBFN ... Forecasting and analysis of complex stochastic dynamical processes with applications in Space weather systems. Environmental ...

- Student Researchon August 13, 2020 at 1:41 pm
We investigate its stochastic nature, reaffirm that it is heavy-tailed as opposed to normally-distributed, and that this is true irrespective of the underlying data. We also show that the heaviness of ...

- Reflex-based models with Machine Learningon May 24, 2019 at 2:21 am
Neural networks Neural networks are a class of models that are ... (x,y,w)$ as follows: \[\boxed{w\longleftarrow w-\eta\nabla_w \textrm{Loss}(x,y,w)}\] Stochastic updates Stochastic gradient descent ...

- Recurrent Neural Networks cheatsheeton November 29, 2018 at 9:51 am
Architecture of a traditional RNN Recurrent neural networks, also known as RNNs, are a class of neural networks that allow previous outputs to be used as inputs while ...

*via Bing News*