Home > Author > François Chollet
1 " Uncrumpling paper balls is what machine learning is about: finding neat representations for complex, highly folded data manifolds. "
― François Chollet , Deep Learning with Python
2 " Some readers are bound to want to take the techniques we’ve introduced here and try them on the problem of forecasting the future price of securities on the stock market (or currency exchange rates, and so on). Markets have very different statistical characteristics than natural phenomena such as weather patterns. Trying to use machine learning to beat markets, when you only have access to publicly available data, is a difficult endeavor, and you’re likely to waste your time and resources with nothing to show for it.Always remember that when it comes to markets, past performance is not a good predictor of future returns—looking in the rear-view mirror is a bad way to drive. Machine learning, on the other hand, is applicable to datasets where the past is a good predictor of the future. "
3 " In practice, experienced machine-learning engineers and researchers build intuition over time as to what works and what doesn’t when it comes to these choices—they develop hyperparameter-tuning skills. But there are no formal rules. If you want to get to the very limit of what can be achieved on a given task, you can’t be content with arbitrary choices made by a fallible human. Your initial decisions are almost always suboptimal, even if you have good intuition. You can refine your choices by tweaking them by hand and retraining the model repeatedly—that’s what machine-learning engineers and researchers spend most of their time doing. But it shouldn’t be your job as a human to fiddle with hyperparameters all day—that is better left to a machine. "
― François Chollet
4 " Currently, most of the job of a deep-learning engineer consists of munging data with Python scripts and then tuning the architecture and hyperparameters of a deep network at length to get a working model—or even to get a state-of-the-art model, if the engineer is that ambitious. "
5 " Not all problems can be solved; just because you’ve assembled examples of inputs X and targets Y doesn’t mean X contains enough information to predict Y. For instance, if you’re trying to predict the movements of a stock on the stock market given its recent price history, you’re unlikely to succeed, because price history doesn’t contain much predictive information. "