The future of Artificial Intelligence in Weather Forecasting

Weather station

Today’s weather forecasts are generated by some of the world’s most sophisticated computers. As you may know, weather forecasts are very unpredictable. This is because the climate is a very complex and volatile phenomenon that requires a great amount of money, data, and time to evaluate. The future may follow a very different path regarding weather forecasting: and that future is A.I.

Read More

Human Brain neuron and Artificial neuron

As you might be already aware, the human brain is made up of billions of neurons and an incredible number of connections between them. Each neuron is connected to multiple other neurons, and they repeatedly exchange information. So whatever activity that we do physically or mentally fires up a certain set of neurons in our brains.

Read More

Tips and tricks for Neural Networks

The following selection of tips aims to make things easier for you. It’s not a must-do list but should be seen as an inspiration. You know the task at hand and can thus best select from the following techniques. They cover a wide area: from augmentation to selecting hyperparameters; many topics are touched upon. Use this selection as a starting point for future research.

Read More

The amazing applications of Graph Neural Networks

The predictive prowess of machine learning is widely hailed as the summit of statistical Artificial Intelligence. Vaunted for its ability to enhance everything from customer service to operations, its numerous neural networks, multiple models, and deep learning deployments are considered an enterprise surety for profiting from data. But according to Franz CEO Jans Aasman, there’s just one tiny problem with this lofty esteem that’s otherwise accurate.

Read More

Black-box and White-box models towards Explainable AI

Black and white box

Let’s say our model needs to learn a recipe for how to make an apple pie. We have the recipes for blueberry pie, cheesecake, shepherd’s pie, and a plain cake recipe. While the rule-based learning approach tries to come up with a set of general rules for making all types of desserts (i.e., eager approach), the case-based learning approach generalizes the information exactly as needed to cover particular tasks. Therefore, it would look for the most similar desserts to apple pie in the available data. Then, it would try to customize with small variations on similar recipes.

Read More

[Paper] IEEE Publishes comprehensive Survey of bottom-up and top-down Neural Processing System Design

In a new paper, a team from the IEEE (Institute of Electrical and Electronics Engineers) provides a comprehensive overview of the bottom-up and top-down design approaches toward neuromorphic intelligence, highlighting the different levels of granularity present in existing silicon implementations and assessing the benefits of the different circuit design styles of neural processing systems.

Read More

[Paper] Simulating Continuum Mechanics with Multi-Scale Graph Neural Networks

Continuum mechanics simulators, numerically solving one or more partial differential equations, are essential tools in many areas of science and engineering, but their performance often limits application in practice. Recent modern machine learning approaches have demonstrated their ability to accelerate spatio-temporal predictions, although, with only moderate accuracy in comparison. Here we introduce MultiScaleGNN, a novel multi-scale graph neural network model for learning to infer unsteady continuum mechanics.

Read More

No code introduction to neural networks

The simple architecture explained – Neural networks have been around for a long time, being developed in the 1960s as a way to simulate neural activity for the development of artificial intelligence systems. However, since then they have developed into a useful analytical tool often used in replace of, or in conjunction with, standard statistical models such as regression or classification as they can be used to predict or more a specific output.

Read More

7 steps to design a basic Neural Network (part 2 of 2)

In Part 1 of 2 of this segment, we saw the limitation of using a traditional prediction model like logistic regression to correctly classify two colors in a noisy dataset. Then, we built our own neural network structure, initialized parameters, and computed the forward propagation activation functions. In this Part 2 of 2, we will complete the build of our neural network model to better classify the color dots in our original dataset. Specifically, we’ll review the cost function, backward propagation, parameters updates, and the final model assembly/prediction.

Read More

7 steps to design a basic Neural Network (part 1 of 2)

This two-part article takes a more holistic, overarching (and yes, less math-y) approach to building a neural network from scratch. Python for completing the network is also included in each of the 7 steps. Part One: (1) Define the network structure, (2) Initialize parameters, and (3) Implement forward propagation. Part Two: (4) Estimate cost, (5) Implement backward propagation, (6) Update parameters, and (7) Make predictions.

Read More

Deep Instinct’s neural networks for cybersecurity attract $100M

Deep Instinct CEO Guy Caspi

The increasingly rich data companies are collecting makes them a more tantalizing target for attacks. But Deep Instinct wants to turn that same data into an enterprise’s greatest defensive asset. Deep Instinct is applying end-to-end deep learning to cybersecurity, an approach that allows it to predict and prevent cyberattacks across a company’s network, according to CEO Guy Caspi.

Read More

Deeplite raises $6M seed to deploy ML on edge with fewer compute resources


Today, the company announced a $6 million seed investment. Boston-based venture capital firm PJC led the round with help from Innospark Ventures, Differential Ventures and Smart Global Holdings. Somel Investments, BDC Capital and Desjardins Capital also participated.

Read More

10 real-life applications of Reinforcement Learning

In Reinforcement Learning (RL), agents are trained on a reward and punishment mechanism. The agent is rewarded for correct moves and punished for the wrong ones. In doing so, the agent tries to minimize wrong moves and maximize the right ones. In this article, we’ll look at some of the real-world applications of reinforcement learning.

Read More
1 2 3 4