Update dream.ipynb

dream.ipynb

@@ -24,7 +24,7 @@
  "It'll be interesting to see what imagery people are able to generate using the described technique. If you post images to Google+, Facebook, or Twitter, be sure to tag them with **#deepdream** so other researchers can check them out too.\n",
  "\n",
  "##Dependences\n",
- "This notebook is designed to have as few depencences as possible:\n",
+ "This notebook is designed to have as few dependencies as possible:\n",
  "* Standard Python scientific stack: [NumPy](http:https://www.numpy.org/), [SciPy](http:https://www.scipy.org/), [PIL](http:https://www.pythonware.com/products/pil/), [IPython](http:https://ipython.org/). Those libraries can also be installed as a part of one of scientific packages for Python, such as [Anaconda](http:https://continuum.io/downloads) or [Canopy](https://store.enthought.com/).\n",
  "* [Caffe](http:https://caffe.berkeleyvision.org/) deep learning framework ([installation instructions](http:https://caffe.berkeleyvision.org/installation.html)).\n",
  "* Google [protobuf](https://developers.google.com/protocol-buffers/) library that is used for Caffe model manipulation."
@@ -66,8 +66,8 @@
  },
  "source": [
  "## Loading DNN model\n",
- "In this notebook we are going to use a [GoogLeNet](https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet) model trained on [ImageNet](http:https://www.image-net.org/) dataset.\n",
- "Feel free to experiment with other models from Caffe [Model Zoo](https://github.com/BVLC/caffe/wiki/Model-Zoo). One particulary interesting [model](http:https://places.csail.mit.edu/downloadCNN.html) was trained in [MIT Places](http:https://places.csail.mit.edu/) dataset. It produced many visuals from the [original blog post](http:https://googleresearch.blogspot.ch/2015/06/inceptionism-going-deeper-into-neural.html)."
+ "In this notebook we are going to use a [GoogleNet](https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet) model trained on [ImageNet](http:https://www.image-net.org/) dataset.\n",
+ "Feel free to experiment with other models from Caffe [Model Zoo](https://github.com/BVLC/caffe/wiki/Model-Zoo). One particularly interesting [model](http:https://places.csail.mit.edu/downloadCNN.html) was trained in [MIT Places](http:https://places.csail.mit.edu/) dataset. It produced many visuals from the [original blog post](http:https://googleresearch.blogspot.ch/2015/06/inceptionism-going-deeper-into-neural.html)."
  ]
  },
  {