danoneata

from typing import (
    List,
    TypeVar,
)

# Type aliases
A = TypeVar('A')
Digit = int
Matrix = List[List[A]]
Grid = Matrix[Digit]

danoneata

{-# LANGUAGE TypeOperators #-}
{-# LANGUAGE GeneralizedNewtypeDeriving #-}   
                                                           
import Control.Applicative
import Data.Char
import Data.List (intersperse)
import Data.Monoid hiding (All, Any)
import Data.Foldable hiding (all, any)
import Prelude hiding (all, any)

danoneata

Course info

• Motivation: Deep learning in vision, speech, text, robotics.

• Deep learning courses:

  • Andrew Ng: Deep Learning
  • fast.ai: Practical Deep Learning For Coders
  • Stanford: CS231n Convolutional Neural Networks for Visual Recognition

• Oxford: Machine Learning

danoneata

from functools import singledispatch


class Document:
    pass


class Paragraph(Document):
    def __init__(self, text):
        self.text = text

danoneata

import argparse
import pdb
import os
import sys

from collections import namedtuple

import numpy as np
import pandas as pd

danoneata

Definition (monoid). A monoid consists of:

1. a set M
2. a binary operation · : M × M → M
3. an element e ∈ M

such that

1. the binary operation is associative, that is, x · (y · z) = (x · y) · z, ∀ x, y, z ∈ M
2. the element e is identity: x · e = x = e · x, ∀ x ∈ M.

danoneata

{-# LANGUAGE DeriveFunctor #-}
{-# LANGUAGE InstanceSigs #-}
{-# LANGUAGE LambdaCase #-}

-- This script is based on Chris Taylor's gist: https://gist.github.com/chris-taylor/4745921
--
-- The main differences are:
-- 1. An interpretation in a different monad, the RWS monad. This idea was also was taken from somewhere else:
--    http://www.cs.uu.nl/docs/vakken/afp/assignment3.html
-- 2. An implementation based on free monads, see the `IOActionFreeMonad.hs` file.

danoneata

import numpy as np
import pdb
from matplotlib import pyplot as plt
from scipy.stats import multivariate_normal


def gauss2d(mu, sigma, to_plot=False):
    w, h = 100, 100

    std = [np.sqrt(sigma[0, 0]), np.sqrt(sigma[1, 1])]

danoneata

"""This code is inspired by the homework 2 from CSC421/2516 Winter 2019,
but I'm taking a more functional approach.

http://www.cs.toronto.edu/~rgrosse/courses/csc421_2019/homeworks/hw2.pdf
http://www.cs.toronto.edu/~rgrosse/courses/csc421_2019/homeworks/maml.py

"""

import autograd.numpy as np
import autograd as ag

danoneata

• Kristen Grauman – Tips for Preparing a Clear Talk slides video
• Patrick Winston – How to Speak videos; see, especially, The Big Four
• Ranjit Jhala – (An Opinionated Talk) On Preparing Good Talks slides video
• Gary Bernhardt – How to Prepare a Talk article
• Iain Murray – Speaking Resources notes