mirror of
https://github.com/saymrwulf/nvidia-AI.summerschool17-notebooks.git
synced 2026-11-20 09:52:58 +00:00
420 lines
336 KiB
Text
420 lines
336 KiB
Text
|
|
{
|
||
|
|
"metadata": {
|
||
|
|
"name": "00-introduction"
|
||
|
|
},
|
||
|
|
"nbformat": 3,
|
||
|
|
"nbformat_minor": 0,
|
||
|
|
"worksheets": [
|
||
|
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Title: Introduction - Neural Computation and Self Organization\n",
|
||
|
|
"Author: Thomas Breuel\n",
|
||
|
|
"Institution: UniKL"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"collapsed": false,
|
||
|
|
"input": [
|
||
|
|
"\n",
|
||
|
|
"from IPython.core.display import Image \n",
|
||
|
|
"def fig(x): return Image(filename=\"Figures/\"+x+\".png\")\n",
|
||
|
|
"from pylab import *\n",
|
||
|
|
"def figs(*args):\n",
|
||
|
|
" for i,f in enumerate(args):\n",
|
||
|
|
" subplot(1,len(args),i+1)\n",
|
||
|
|
" axis('off')\n",
|
||
|
|
" imshow(imread(\"Figures/\"+f+\".png\"),cmap=cm.gray)"
|
||
|
|
],
|
||
|
|
"language": "python",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"prompt_number": 2
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "heading",
|
||
|
|
"level": 1,
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Course Mechanics"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(Home Page)\n",
|
||
|
|
"\n",
|
||
|
|
"http://ncso.iupr.com/"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(Exercise Sessions)\n",
|
||
|
|
"\n",
|
||
|
|
"TBA"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Handing in Exercises is mandatory.\n",
|
||
|
|
"\n",
|
||
|
|
"Bring your completed exercises to your oral exam."
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(Python)\n",
|
||
|
|
"\n",
|
||
|
|
"All practical exercises are in Python using iPython Notebooks."
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "heading",
|
||
|
|
"level": 1,
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Python"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(About Python)\n",
|
||
|
|
"\n",
|
||
|
|
"Dynamic, object-oriented programming language.\n",
|
||
|
|
"\n",
|
||
|
|
"Python is widely used for scripting, desktop apps, web apps, scientific and numerics, graphics, and games.\n",
|
||
|
|
"\n",
|
||
|
|
"Companies making extensive use of Python: Google, Microsoft Research, Yahoo Maps/Groups, Blender, Civ 4, Industrial Light and Magic, Walt Disney Animation, NASA...\n",
|
||
|
|
"\n",
|
||
|
|
"Multiple implementations: Python, IronPython (Python-CLR, CE), Cython, PyPy (JIT), jython (Python-JVM)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"collapsed": false,
|
||
|
|
"input": [
|
||
|
|
"# Python example: quicksort\n",
|
||
|
|
"from random import choice,sample\n",
|
||
|
|
"\n",
|
||
|
|
"def quicksort(l):\n",
|
||
|
|
" if len(l)<2: return l\n",
|
||
|
|
" pivot = choice(l)\n",
|
||
|
|
" lo = [x for x in l if x<pivot]\n",
|
||
|
|
" eq = [x for x in l if x==pivot]\n",
|
||
|
|
" hi = [x for x in l if x>pivot]\n",
|
||
|
|
" return quicksort(lo)+eq+quicksort(hi)\n",
|
||
|
|
"\n"
|
||
|
|
],
|
||
|
|
"language": "python",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"prompt_number": 7
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"collapsed": false,
|
||
|
|
"input": [
|
||
|
|
"l = sample(range(1000),10)\n",
|
||
|
|
"print l\n",
|
||
|
|
"print quicksort(l)"
|
||
|
|
],
|
||
|
|
"language": "python",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"output_type": "stream",
|
||
|
|
"stream": "stdout",
|
||
|
|
"text": [
|
||
|
|
"[60, 240, 70, 754, 27, 67, 786, 57, 100, 965]\n",
|
||
|
|
"[27, 57, 60, 67, 70, 100, 240, 754, 786, 965]\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"prompt_number": 8
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(Python properties)\n",
|
||
|
|
"\n",
|
||
|
|
"- interactive\n",
|
||
|
|
"- object-oriented\n",
|
||
|
|
"- functional constructs\n",
|
||
|
|
"- dynamically typed\n",
|
||
|
|
"- duck typed\n",
|
||
|
|
"- reflective\n",
|
||
|
|
"- interpreted (usually)\n",
|
||
|
|
"- indentation is significant"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"collapsed": false,
|
||
|
|
"input": [
|
||
|
|
"## iPython Notebooks\n",
|
||
|
|
"fig(\"ipython-notebook\")"
|
||
|
|
],
|
||
|
|
"language": "python",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"output_type": "pyout",
|
||
|
|
"png": "iVBORw0KGgoAAAANSUhEUgAAAlgAAAIXCAIAAADPCrcyAAAACXBIWXMAAAsTAAALEwEAmpwYAAAA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\nDDNZQ26iFmcLeY2CCFGjGVkm
|
||
|
|
"prompt_number": 9,
|
||
|
|
"text": [
|
||
|
|
"<IPython.core.display.Image at 0x2c0f890>"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"prompt_number": 9
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(Learning Python)\n",
|
||
|
|
"\n",
|
||
|
|
"- quick introduction in exercises\n",
|
||
|
|
"- lots of free materials on the web\n",
|
||
|
|
"- lots of books (e.g., 150 books on Amazon; cf. 626 for Java, 50 for Ruby)\n",
|
||
|
|
"- if you know Matlab, it's fairly similar (there are tables for comparison)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(Important Software)\n",
|
||
|
|
"\n",
|
||
|
|
"- Python 2.x\n",
|
||
|
|
"- Ubuntu (easiest to install)\n",
|
||
|
|
"- NumPy\n",
|
||
|
|
"- SciPy\n",
|
||
|
|
"- Matplotlib\n",
|
||
|
|
"- scikit.learn\n",
|
||
|
|
"- gimp\n",
|
||
|
|
"- UNIX shell scripts"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "heading",
|
||
|
|
"level": 1,
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Why study neural computing?"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(course contents)\n",
|
||
|
|
"\n",
|
||
|
|
"Introductions to:\n",
|
||
|
|
"\n",
|
||
|
|
"- machine learning\n",
|
||
|
|
"- neural network algorithms\n",
|
||
|
|
"- neuromorphic algorithms and hardware\n",
|
||
|
|
"- behavioral robotics\n",
|
||
|
|
"- bioinformatics"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(big computer science questions)\n",
|
||
|
|
"\n",
|
||
|
|
"- better machine learning\n",
|
||
|
|
"- higher memory density\n",
|
||
|
|
"- lower power consumption\n",
|
||
|
|
"- robustness to component failure\n",
|
||
|
|
"- larger degrees of parallelism\n",
|
||
|
|
"- asynchronous operation"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"collapsed": false,
|
||
|
|
"input": [
|
||
|
|
"# Human Brain Project\n",
|
||
|
|
"figs(\"hbp\")\n",
|
||
|
|
"\n"
|
||
|
|
],
|
||
|
|
"language": "python",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"output_type": "display_data",
|
||
|
|
"png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAADZCAYAAAA9iLuQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\neZZ6CXdMTfLz33eIqWqR//7q
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"prompt_number": 3
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Brain simulation: http://www.humanbrainproject.eu/index.html\n",
|
||
|
|
"\n",
|
||
|
|
"EU 100 million per year"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"(Human Brain Project)\n",
|
||
|
|
"\n",
|
||
|
|
"Life sciences:\n",
|
||
|
|
"\n",
|
||
|
|
"- sequencing\n",
|
||
|
|
"- imaging\n",
|
||
|
|
"- scanning\n",
|
||
|
|
"- connectome project\n",
|
||
|
|
"\n",
|
||
|
|
"Information Technology:\n",
|
||
|
|
"\n",
|
||
|
|
"- distributed database technology\n",
|
||
|
|
"- cloud computing\n",
|
||
|
|
"- massive parallelism\n",
|
||
|
|
"- massively distributed numerical simulations\n",
|
||
|
|
"- multiscale modeling\n",
|
||
|
|
"- neuroinformatics\n",
|
||
|
|
"- VLSI and brain-inspired hardware"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"collapsed": false,
|
||
|
|
"input": [
|
||
|
|
"# Obama's BRAIN Initiative\n",
|
||
|
|
"figs(\"obama-brain\")\n",
|
||
|
|
"\n"
|
||
|
|
],
|
||
|
|
"language": "python",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"output_type": "display_data",
|
||
|
|
"png": "iVBORw0KGgoAAAANSUhEUgAAAXMAAADzCAYAAAB0ffb+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTf0Ca2ostz7mU3l4IsX3KXaj
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"prompt_number": 6
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"BRAIN Initiative: http://www.whitehouse.gov/blog/2013/04/02/brain-initiative-challenges-researchers-unlock-mysteries-human-mind\n",
|
||
|
|
"\n",
|
||
|
|
"- real-time brain mapping\n",
|
||
|
|
"- complex neural circuit modeling"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"It's a graduate course. It's intended to get you thinking about research and \"big picture\" questions.\n",
|
||
|
|
"\n",
|
||
|
|
"We touch on many topics, but you need to deepen your understanding through reading."
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "heading",
|
||
|
|
"level": 1,
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Course Contents"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Neural Computation\n",
|
||
|
|
"\n",
|
||
|
|
"- basic structure of neurons\n",
|
||
|
|
"- Hodgkin-Huxley model, differential equations, simulations\n",
|
||
|
|
"- simplified neural models, scale problem\n",
|
||
|
|
"- computational universality\n",
|
||
|
|
"- associative memory and dynamic systems\n",
|
||
|
|
"- perceptrons and perceptron learning"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Supervised Learning\n",
|
||
|
|
"\n",
|
||
|
|
"- Bayesian Decision Theory\n",
|
||
|
|
"- linear least squares, logistic regression\n",
|
||
|
|
"- multilayer perceptrons\n",
|
||
|
|
"- posterior probabilities from neural networks\n",
|
||
|
|
"- convolutional neural networks"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Unsupervised Learning\n",
|
||
|
|
"\n",
|
||
|
|
"- principal component analysis\n",
|
||
|
|
"- k-means and EM algorithms\n",
|
||
|
|
"- self-organizing maps"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Also:\n",
|
||
|
|
"\n",
|
||
|
|
"- review some math\n",
|
||
|
|
"- data-parallel computing and matrix languages"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"Goals:\n",
|
||
|
|
"\n",
|
||
|
|
"- understand neural networks as computational systems\n",
|
||
|
|
"- be able to apply neural network learning to solving practical problems\n",
|
||
|
|
"- get a good background in machine learning and be able to apply it\n",
|
||
|
|
"- get ready to develop large-scale neural network simulations\n",
|
||
|
|
"\n",
|
||
|
|
"NB: ML with neural networks is very similar to ML with support vector machines and other approaches"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"collapsed": false,
|
||
|
|
"input": [],
|
||
|
|
"language": "python",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": []
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {}
|
||
|
|
}
|
||
|
|
]
|
||
|
|
}
|