The Hopfield Network is a is a form of recurrent artificial neural network described by John Hopfield in 1982.
An Hopfield network is composed by N fully-connected neurons and N² weighted edges. Moreover, each node has a state which consists of a spin equal either to +1 or -1.
This kind of network is deployed when one has a set of states (namely vectors of spins) and one wants the network to remember them. In mathematical terms we build an Hamiltonian in the data space in a manner that its minima are in some particular points we choose: the memories.
Application of machine learning are, nowadays, endless. There are models out there already trained and data that need nothing but to be fitted.
When one deals with Machine Learning applications it often tricky deciding on which hardware train the model and offload the inference.
Intel® has introduced openVINO® that help deploy models (mostly related to computer vision) to any Intel® device, no matter if they are CPUs, GPUs, FPGAs or a Neural Compute Stick with a MYRIAD chip.
Clustering is a Machine Learning technique that involves the grouping of data points. Given a set of data points, we can use a clustering algorithm to classify each data sample into a specific group (cluster).
Clustering is a method of unsupervised learning and is a common technique for statistical data analysis used in many fields. The hope of the data scientist is that samples in the same cluster have similar properties, features or behaviour. For instance, one could run clustering on cancers’ samples, and the hope is that samples in the same group belong to the same cancer subtype .
Every mobile application at a certain point needs an upgrade, bugfixes and new features have to be delivered to users. I recently realised how it is simple to use serverless to provide upgrades to existing apps.
Once deployed, serverless apps respond and automatically scale up and down as needed. Finally, when a serverless function is sitting idle, it doesn’t cost anything.
I will discuss an example of a serverless function that answers calls from mobile applications written with Flutter.
Applications of Artificial Intelligence are endless. I gather a RaspberryPi4 and an Intel Neural Compute Stick® and played with them. A Raspberry is an on-board computer with infinities capabilities, but it is not enough powerful to run complex neural networks. Here it come the NCS enabling new possibilities. When connected together they are a powerful instrument able to load complex neural network architectures in a small form-factor and with low energy consumption.
I combined them together to build a AI-enabled web server. With any device connected to the home network it is possible to watch a live streaming from a…
One of my side projects involved an app to display the temperature of the CPU on a MacBook. At the time I made it there wasn’t an app or functionality to display the CPU’s temperature on the menu bar of a Mac. That’s a quite useful information about the stress of the processor. So, I decided to develop it on my own. Consequently I start working with swift language and learned many interesting stuff.
Here it is the simple view of this. It shows the CPU, Battery and harddisk (if any) temperature. Nothing more nothing less, it is quite essential…
Today I will show you how to create a simple bot using Julia language.
The bot I am going to describe is quite generic, it can read messages, reply and store the status of the conversation with multiple users.
I will use Telegram, since it provides easy access to API (https://core.telegram.org/bots).
When interacting with the bot users can be at different steps of the conversation, we’will call them states. This states need to be stored, so we will give the bot a memory of its interactions.
The bot we are going to describe stores some user states in a database…
Today I will talk about one of my most favourite natural laws: the so-called Zipf.
Zipf’s law is particularly interesting because despite its semplicity it is present everywhere in our life. You don’t know but it is.
But it is even more…
Ph.D. student in Complex Systems for Life Sciences. Interested in physics, ML application, community detection and coding.