Notes

While Active Learning looks for the most informative points to recover a true underlying function, Bayesian Optimization is just interested to find the maximum of that function. In Bayesian Optimization, we ask for the best way to find sequentially a set of points $x_{1}, \dots, x_{n}$ to find $\max_{x \in \mathcal{X}} f(x)$ for a certain unknown function $f$. This is what the whole thing is about. Definitions First we will introduce some useful definitions in this context. These were also somewhat introduced in N-Bandit Problem, which is one of the classical optimization problems we can find in the literature. ...

We want to optimize the parts of the datacenter hardware such that the cost of operating the datacenter as a whole would be lower, we need to think about it as a whole. Datacenter CPUs Desktop CPU vs Cloud CPU Isolation: Desktop CPUs have low isolation, they are used by a single user. Cloud CPUs have high isolation, they are shared among different users. Workload and performance: usually high workloads and moving a lot of data around. They have a spectrum of low and high end cores, so that if you have high parallelism you can use lower cores, while for resource intensive tasks, its better to have high end cores, especially for latency critical tasks. ...

Introduzione a OOP Per la definizione di classe andare a guardare Object Orientation, però lo ripeto in questa occasione, è solamente un modello su cui andare a costruire degli oggetti. Capisaldi Incapsulazione (con interfaccia, base per la documentazione) Astrazione Ereditarietà Dispatch dinamico Inheritance to avoid code duplication Subtyping to express classification Overriding to specialize methods Dynamic binding to adapt reused algorithms Costruttori Il costruttore è un codice utilizzato per inizializzare correttamente lo stato interno. Le regole sono le stesse dei metodi sovraccaricati (dinamica per la chiamata, statica per il numero dei parametri che prende in input). ...

Introduzione alla Teoria dei Tipi History of Languages Research The root of languages research are in: in logic and computations (even before computers!). Artificial intelligence (Lisp, constrained solvers, the original logical AI we studied in (Russell & Norvig 2009)). Algebra and symbolic reasoning. Definizione di Tipo Un metodo sintattico praticabile per dimostrare l’assenza di determinati comportamenti del programma, fatto classificando le unità sintattiche in base ai tipi di valore che assumono ...

This note is just a collection of past useful notes to know to apply machine learning methods for the analysis of topics interesting in the neural sciences. Estimators You need to know all Parametric Modeling. We want to estimate unknown random variables with some observations. Maximum Likelihood See Bayesian Linear Regression. Bias-Variance Decomposition Fisher Information See Parametric Modeling#Fisher information. Applications Echo-locating bats Egyptian fruit flies bats use echo location to locate the target, emitting clicks and capturing echo to navigate the environment. Bats use to click slightly left and right compared to their direction of motion. It is interesting to observe and study how these bats are clicking around to move. ...

The Potassium Exchange values We use the measurement by Cole and Curthis 40mS/cm squared was their measure of Potassium ions leaving the membrane $$ \Delta Q = Idt = GA \Delta E dt $$The potassium concentration is 0.155 moles per litre. Where $G$ is the conductance per unit area, $A$ the membrane surface, $E$ voltage deflection Remember that the conductance is the reciprocal of the resistance, and $V = IR \implies I = \frac{V}{R} = GV$ ...

Vision is THE most important sense for humans. Most of the information we get is through vision 90% vision This is true for humans, but for mice for example it is different, they have probably a 64x64 pixel resolution equivalent. For humans, visual data is more important, it is faster compared to speech and other senses. We can also see this when we are talking about quantity of neurons: 30% of neurons in the cortex are for vision. 8% tactile, touch 3% hearing Rest is for other Precision of human vision Human vision is estimated to be about 576 Megapixels of data (3M snapshots patched together with saccades, that has that pixel image value), since it can distinguish 0.6arc-minutes (0.01 degrees). There is an estimate of about 60kk ± 12kk rods and 3kk ±0.5kk cones. This means that the image is constructed by high resolution saccades (patches). ...

We have a classical exploration-exploitation tradeoff, see Reinforcement Learning, a introduction. Why would animals explore, even if there is no immediate reward based on it? Animals are able to adapt and explore nonetheless. It would be thus nice to understand and implement these features in artificial systems. We will attack this from an evolutionary psychology perspective: Playfulness and intrinsic motivation. Curiosity Here we will talk about why animals are pushed to explore. ...

Here we attempt to answer what is memory, how is it stored and retrieved. Human Memory Definition of Memory Memory is a process by which information is: Encoded Stored Retrieved The brain has different types of memories, and certain brain regions are specialized for this task. Ebbinghaus Curves Other experiments destroy parts of the cortex and correlate this with recall. Types of memory We have the memory pipeline: ...

Synapses are the connections that exist between one neuron and another, so we can think of them as the communication channel between neurons. Gap Junctions Electrical based These are also called Gap Junctions These are more direct connections between neurons, allowing excitation ions to pass through quite directly (this is the difference compared to chemically based ones). It’s a circuit more similar to an electronic one because it’s faster. The end of the presynapsic part is called axon bouton, or axon terminal. Another characteristic of these kinds of synapses is that they are two-way channels. ...